API Reference
Vision Studio API Documentation¶
This document provides details on the Vision Studio API, a comprehensive set of endpoints for image generation, editing, captioning, video processing, and analysis across multiple AI providers.
Table of Contents¶
Introduction & Setup
API Endpoints
Introduction¶
The Vision Studio API provides a unified interface organized by functional tags that span multiple providers. High-level capabilities include:
- Prompt Enhancement: AI-powered prompt optimization for better image generation results
- Media Captioning: Image and video captioning utilities
- Image Editing / Image Editing Generation: Deterministic edits and generative edits for images
- Image Generation: Text-to-image and guided image generation
- Video Editing / Video Editing Generation: Deterministic and generative video operations
- Video Generation: Text/image/video-to-video generation
- Audio Generation: Text-to-speech
- Upload: Provider-specific asset upload helpers
- Status: Async job status and cancellation
- LoRA Project Management / LoRA Training: Tailored model lifecycle and training APIs
All providers support both synchronous and asynchronous processing where applicable.
Authentication¶
The endpoints in this API require authentication. Use the X-API-Key header with your API key:
API Reference¶
Vision Studio API 1.0.0¶
Prompt Enhancement¶
POST /api/v1/prompt/enhance-prompt¶
Enhance Prompt
Description
Enhance an existing prompt to create more beautiful and professional image generation results.
This endpoint takes a basic image generation prompt and transforms it into a detailed, professional photography description with rich visual details, lighting conditions, and atmospheric elements.
Args:
- prompt : The original basic prompt to enhance
- temperature (float): Temperature for prompt generation (0.0-2.0), controls randomness
- model_provider : Model provider to use ("openai" or "gemini")
Returns: Json response with success status and the result containing the generated prompt and metadata.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"prompt": {
"type": "string",
"minLength": 3,
"title": "Prompt",
"description": "The original prompt to enhance for better image generation results",
"examples": [
"A mountain landscape with a lake",
"A cozy coffee shop interior",
"Professional headshot of a business person"
]
},
"temperature": {
"type": "number",
"maximum": 2.0,
"minimum": 0.0,
"title": "Temperature",
"description": "Temperature for prompt generation",
"default": 0.7
},
"model_provider": {
"$ref": "#/components/schemas/LlmProvider",
"description": "Model provider to use",
"default": "openai"
}
},
"type": "object",
"required": [
"prompt"
],
"title": "PromptEnhancementRequest",
"description": "Request model for prompt enhancement."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/prompt/adapt-background-prompt¶
Prompt Background Adapt
Description
Generate a prompt to adapt an existing background image for specific audience and location.
This endpoint creates concise prompts that describe how to modify an existing background image with location-specific color palettes, visual elements, and mood that resonates with the target audience.
Args:
- audience : Target audience for the image (e.g., "families", "young adults", "professionals")
- location : Geographic location for the image (e.g., "Paris", "Tokyo", "Morocco")
- temperature (float): Temperature for prompt generation (0.0-2.0), it controls the randomness of the prompt. Higher values create more varied prompts.
- model_provider : Model provider to use ("openai" or "gemini")
Returns: Json response with success status and the result containing the generated prompt and metadata.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"audience": {
"type": "string",
"minLength": 1,
"title": "Audience",
"description": "Target audience for the image",
"examples": [
"families",
"young adults",
"professionals"
]
},
"location": {
"type": "string",
"minLength": 1,
"title": "Location",
"description": "Geographic location for the image",
"examples": [
"Paris",
"Tokyo",
"Morocco"
]
},
"temperature": {
"type": "number",
"maximum": 2.0,
"minimum": 0.0,
"title": "Temperature",
"description": "Temperature for prompt generation",
"default": 0.7
},
"model_provider": {
"$ref": "#/components/schemas/LlmProvider",
"description": "Model provider to use",
"default": "openai"
}
},
"type": "object",
"required": [
"audience",
"location"
],
"title": "BackgroundAssetAdaptationRequest",
"description": "Request model for background asset adaptation prompt generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/prompt/generate-background-prompt¶
Prompt Generate Background
Description
Generate a prompt to create a background image from scratch for specific audience and location.
This endpoint creates detailed prompts for generating background images that capture the essence of a specific location while appealing to the target audience's preferences.
Args:
- audience : Target audience for the image (e.g., "families", "children", "seniors")
- location : Geographic location for the image (e.g., "Southern France", "Japan", "Italy")
- temperature (float): Temperature for prompt generation (0.0-2.0), it controls the randomness of the prompt. Higher values create more varied prompts.
- model_provider : Model provider to use ("openai" or "gemini")
Returns: Json response with success status and the result containing the generated prompt and metadata.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"audience": {
"type": "string",
"minLength": 1,
"title": "Audience",
"description": "Target audience for the image",
"examples": [
"families",
"children",
"seniors"
]
},
"location": {
"type": "string",
"minLength": 1,
"title": "Location",
"description": "Geographic location for the image",
"examples": [
"Southern France",
"Japan",
"Italy"
]
},
"temperature": {
"type": "number",
"maximum": 2.0,
"minimum": 0.0,
"title": "Temperature",
"description": "Temperature for prompt generation",
"default": 0.7
},
"model_provider": {
"$ref": "#/components/schemas/LlmProvider",
"description": "Model provider to use",
"default": "openai"
}
},
"type": "object",
"required": [
"audience",
"location"
],
"title": "BackgroundCreationRequest",
"description": "Request model for background creation prompt generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/prompt/generate-image-prompt¶
Prompt Generate Image Creation
Description
Generate a prompt for image creation from scratch for specific audience and location.
This endpoint creates detailed prompts for generating complete images that resonate with the target audience and capture the essence of a specific location.
Args:
- audience : Target audience for the image (e.g., "families", "young adults", "professionals")
- location : Geographic location for the image (e.g., "Paris", "Tokyo", "Morocco")
- temperature (float): Temperature for prompt generation (0.0-2.0), it controls the randomness of the prompt. Higher values create more varied prompts.
- model_provider : Model provider to use ("openai" or "gemini")
Returns: Json response with success status and the result containing the generated prompt and metadata.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"audience": {
"type": "string",
"minLength": 1,
"title": "Audience",
"description": "Target audience for the image",
"examples": [
"families",
"young adults",
"professionals"
]
},
"location": {
"type": "string",
"minLength": 1,
"title": "Location",
"description": "Geographic location for the image",
"examples": [
"Paris",
"Tokyo",
"Morocco"
]
},
"temperature": {
"type": "number",
"maximum": 2.0,
"minimum": 0.0,
"title": "Temperature",
"description": "Temperature for prompt generation",
"default": 0.7
},
"model_provider": {
"$ref": "#/components/schemas/LlmProvider",
"description": "Model provider to use",
"default": "openai"
}
},
"type": "object",
"required": [
"audience",
"location"
],
"title": "ImageCreationRequest",
"description": "Request model for image creation prompt generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/prompt/adapt-subject-prompt¶
Prompt Adapt Subject
Description
Generate a prompt for a custom model based on subject, target audience, and location.
This endpoint creates image generation prompts specifically tailored to generate images of the specified subject that resonate with the specified audience in the given location context.
Args:
- subject : Main subject for the image (e.g., "cat", "dog", "person")
- audience : Target audience for the image (e.g., "families", "professionals", "children")
- location : Geographic location for the image (e.g., "Paris", "Tokyo", "New York")
- model_provider : Model provider to use ("openai" or "gemini")
- temperature (float): Temperature for prompt generation (0.0-2.0), it controls the randomness of the prompt. Higher values create more varied prompts.
Returns: Json response with success status and the result containing the generated prompt and metadata.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"subject": "string",
"audience": "string",
"location": "string",
"temperature": 10.12,
"model_provider": "openai"
}
Schema of the request body
{
"properties": {
"subject": {
"type": "string",
"minLength": 1,
"title": "Subject",
"description": "Main subject for the image",
"examples": [
"cat",
"dog",
"person"
]
},
"audience": {
"type": "string",
"minLength": 1,
"title": "Audience",
"description": "Target audience for the image",
"examples": [
"families",
"professionals",
"children"
]
},
"location": {
"type": "string",
"minLength": 1,
"title": "Location",
"description": "Geographic location for the image",
"examples": [
"Paris",
"Tokyo",
"New York"
]
},
"temperature": {
"type": "number",
"maximum": 2.0,
"minimum": 0.0,
"title": "Temperature",
"description": "Temperature for prompt generation",
"default": 0.7
},
"model_provider": {
"$ref": "#/components/schemas/LlmProvider",
"description": "Model provider to use",
"default": "openai"
}
},
"type": "object",
"required": [
"subject",
"audience",
"location"
],
"title": "SubjectEnhancementRequest",
"description": "Request model for subject enhancement prompt generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/prompt/generate-subject-pose-prompt¶
Prompt Generate Subject Pose
Description
Generate a detailed image generation prompt for a subject in a specific pose and viewshot.
This endpoint creates prompts for generating images of subjects with unique poses and viewshot angles, ensuring the subject is complete and fully visible against a pure white background.
Args:
- subject : The subject to generate a pose prompt for (e.g., "cat", "dog", "person")
- temperature (float): Temperature for prompt generation (0.0-2.0), it controls the randomness of the prompt. Higher values create more varied prompts.
- model_provider : Model provider to use ("openai" or "gemini")
Returns: Json response with success status and the result containing the generated prompt and metadata.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"subject": {
"type": "string",
"minLength": 1,
"title": "Subject",
"description": "The subject to generate a pose prompt for",
"examples": [
"cat",
"dog",
"person"
]
},
"temperature": {
"type": "number",
"maximum": 2.0,
"minimum": 0.0,
"title": "Temperature",
"description": "Temperature for prompt generation",
"default": 0.7
},
"model_provider": {
"$ref": "#/components/schemas/LlmProvider",
"description": "Model provider to use",
"default": "openai"
}
},
"type": "object",
"required": [
"subject"
],
"title": "SubjectPosePromptRequest",
"description": "Request model for subject pose prompt generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/prompt/enhance-prompt¶
Bria Enhance Prompt
Description
Enhance a prompt using LLama 3.
Args:
- prompt: The text prompt to enhance.
Returns: Json response with success status and the result containing the generated prompt.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Media Captioning¶
POST /api/v1/caption/image¶
Caption Image
Description
Generate a caption for an image from a URL.
Args:
- image_url: URL of the image to caption.
- Example:
https://images.pexels.com/photos/31976103/pexels- photo-31976103.jpeg - mode: Captioning mode (simple, expert, image_tagging)
- model_provider: Model provider (openai or gemini)
- nbr_tags: Number of tags to generate (only relevant for image tagging mode).
- possible_tags: List of possible tags to generate (only relevant for image tagging mode).
- access_token: API key for authentication.
- captioning_client: Captioning client instance.
Returns: Json response with success status and the result containing the generated caption and metadata.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image_url": "string",
"mode": "simple",
"model_provider": "openai",
"nbr_tags": 0,
"possible_tags": null
}
Schema of the request body
{
"properties": {
"image_url": {
"type": "string",
"minLength": 1,
"format": "uri",
"title": "Image Url",
"description": "URL of the image to caption",
"examples": [
"https://images.pexels.com/photos/31976103/pexels-photo-31976103.jpeg",
"https://images.pexels.com/photos/1234567/pexels-photo-1234567.jpeg"
]
},
"mode": {
"$ref": "#/components/schemas/ImageCaptionMode",
"description": "Captioning mode",
"default": "simple"
},
"model_provider": {
"$ref": "#/components/schemas/LlmProvider",
"description": "Model provider to use",
"default": "openai"
},
"nbr_tags": {
"type": "integer",
"maximum": 20.0,
"minimum": 1.0,
"title": "Nbr Tags",
"description": "Number of tags to generate (only for image_tagging mode)",
"default": 5
},
"possible_tags": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Possible Tags",
"description": "Possible tags to choose from (only for image_tagging mode)",
"examples": [
[
"nature",
"landscape",
"city",
"architecture"
]
]
}
},
"type": "object",
"required": [
"image_url",
"possible_tags"
],
"title": "ImageCaptionRequest",
"description": "Request model for image captioning."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/caption/video¶
Caption Video
Description
Generate a caption or a list of tags for a video using Google Gemini.
Args:
- video_url: URL of the video to caption.
- Example:
https://media.w3.org/2010/05/sintel/trailer.mp4 - mode: Captioning mode. Possible values: simple, expert, detailed, tagging, segment_timestamps, segment_timestamps_descriptive, segment_timestamps_tags
- nbr_tags: Number of tags to generate (only relevant for image tagging mode).
- storage_client: Google Cloud Storage client instance.
- gemini_client: Vertex AI Gemini client instance.
Returns: Json response with success status and the result containing the generated caption and metadata.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"video_url": {
"type": "string",
"minLength": 1,
"format": "uri",
"title": "Video Url",
"description": "URL of the video to caption",
"examples": [
"https://media.w3.org/2010/05/sintel/trailer.mp4"
]
},
"mode": {
"$ref": "#/components/schemas/VideoCaptionMode",
"description": "Video captioning mode",
"default": "simple"
},
"nbr_tags": {
"type": "integer",
"maximum": 20.0,
"minimum": 1.0,
"title": "Nbr Tags",
"description": "Number of tags to generate (only for tagging modes)",
"default": 5
}
},
"type": "object",
"required": [
"video_url"
],
"title": "VideoCaptionRequest",
"description": "Request model for video captioning."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Image Generation¶
POST /api/v1/bria/image/generation/generate-image¶
Bria Generate Image
Description
Generate high-quality images using BRIA's base model.
Args:
- bria_model_version: Model version to use.
- prompt: Text description of the desired image (English only).
- num_results: Number of images to generate. Use 1 when using guidance methods. Maximum value is 4.
- aspect_ratio: Image aspect ratio.
- sync: If True, wait for results. If False, return URLs immediately.
- steps_num: Number of refinement iterations (20-50).
- text_guidance_scale: Text adherence strength (1-10).
- prompt_enhancement: Use LLama 3 to enhance prompt.
- seed (optional): Seed for reproducible results.
- negative_prompt (optional): Elements to exclude from generation.
- medium (optional): Output medium type ("photography" or "art").
- guidance_method_1 (optional): First guidance method type. Supported guidance methods are: "controlnet_canny", "controlnet_depth", "controlnet_recoloring", "controlnet_color_grid".
- guidance_method_1_scale (optional): Impact of first guidance method (0.0-1.0).
- guidance_method_1_image_file (optional): Base64 encoded image for first guidance method. Required if guidance_method_1 is specified.
- guidance_method_1_image_url (optional): URL of image for first guidance method. Required if guidance_method_1 is specified.
- guidance_method_2 (optional): Second guidance method type. Supported guidance methods are: "controlnet_canny", "controlnet_depth", "controlnet_recoloring", "controlnet_color_grid".
- guidance_method_2_scale (optional): Impact of second guidance method (0.0-1.0).
- guidance_method_2_image_file (optional): Base64 encoded image for second guidance method. Required if guidance_method_2 is specified.
- guidance_method_2_image_url (optional): URL of image for second guidance method. Required if guidance_method_2 is specified.
- image_prompt_mode (optional): IP-Adapter mode. Supported modes are : "regular", "style_only".
- image_prompt_file (optional): Base64 encoded image for IP-Adapter.
- image_prompt_urls (optional): List of image URLs for IP-Adapter.
- image_prompt_scale (optional): Impact of IP-Adapter (0.0-1.0).
- access_token: API key for authentication.
- bria_client: BRIA API client.
Returns: Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"bria_model_version": "2.3",
"prompt": "string",
"aspect_ratio": "1:1",
"num_results": 0,
"sync": true,
"steps_num": 0,
"text_guidance_scale": 10.12,
"prompt_enhancement": true,
"enhance_image": true,
"prompt_content_moderation": true,
"content_moderation": true,
"ip_signal": true,
"seed": null,
"negative_prompt": null,
"medium": null,
"guidance_method_1": null,
"guidance_method_1_scale": null,
"guidance_method_1_image_url": null,
"guidance_method_1_image_file": null,
"guidance_method_2": null,
"guidance_method_2_scale": null,
"guidance_method_2_image_url": null,
"guidance_method_2_image_file": null,
"image_prompt_mode": null,
"image_prompt_file": null,
"image_prompt_urls": null,
"image_prompt_scale": null
}
Schema of the request body
{
"properties": {
"bria_model_version": {
"type": "string",
"enum": [
"2.3",
"3.2"
],
"title": "Bria Model Version",
"description": "BRIA model version to use",
"default": "3.2"
},
"prompt": {
"type": "string",
"minLength": 4,
"title": "Prompt",
"description": "Text description of the desired image (English only).",
"examples": [
"A mountain landscape with a lake",
"A cozy coffee shop interior",
"Professional headshot of a business person"
]
},
"aspect_ratio": {
"type": "string",
"enum": [
"1:1",
"2:3",
"3:2",
"3:4",
"4:3",
"16:9",
"9:16",
"4:5",
"5:4"
],
"title": "Aspect Ratio",
"description": "Image aspect ratio",
"default": "1:1"
},
"num_results": {
"type": "integer",
"maximum": 4.0,
"minimum": 1.0,
"title": "Num Results",
"description": "Number of images to generate",
"default": 1
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results",
"default": true
},
"steps_num": {
"type": "integer",
"maximum": 50.0,
"minimum": 20.0,
"title": "Steps Num",
"description": "Number of refinement iterations",
"default": 30
},
"text_guidance_scale": {
"type": "number",
"maximum": 10.0,
"minimum": 1.0,
"title": "Text Guidance Scale",
"description": "Text adherence strength",
"default": 5.0
},
"prompt_enhancement": {
"type": "boolean",
"title": "Prompt Enhancement",
"description": "Use LLama 3 to enhance prompt",
"default": false
},
"enhance_image": {
"type": "boolean",
"title": "Enhance Image",
"description": "Generates images with richer details, sharper textures, and enhanced clarity",
"default": false
},
"prompt_content_moderation": {
"type": "boolean",
"title": "Prompt Content Moderation",
"description": "When enabled (default: true), the input prompt is scanned for NSFW or ethically restricted terms before image generation.",
"default": false
},
"content_moderation": {
"type": "boolean",
"title": "Content Moderation",
"description": "When enabled, applies content moderation to both input visuals and generated outputs.",
"default": false
},
"ip_signal": {
"type": "boolean",
"title": "Ip Signal",
"description": "When enabled, adds an IP signature to the generated images.",
"default": false
},
"seed": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Seed",
"description": "Seed for reproducible results"
},
"negative_prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Negative Prompt",
"description": "Elements to exclude",
"examples": [
"text",
"logo",
"watermark",
"background"
]
},
"medium": {
"anyOf": [
{
"type": "string",
"enum": [
"photography",
"art"
]
},
{
"type": "null"
}
],
"title": "Medium",
"description": "Output medium type"
},
"guidance_method_1": {
"anyOf": [
{
"$ref": "#/components/schemas/ControlnetType"
},
{
"type": "null"
}
],
"description": "Guidance method 1",
"examples": [
"controlnet_canny",
"controlnet_depth"
]
},
"guidance_method_1_scale": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Guidance Method 1 Scale",
"description": "Impact of first guidance method"
},
"guidance_method_1_image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Guidance Method 1 Image Url",
"description": "URL of the image to use for guidance method 1",
"examples": [
"https://images.pexels.com/photos/31976103/pexels-photo-31976103.jpeg"
]
},
"guidance_method_1_image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Guidance Method 1 Image File",
"description": "Base64 encoded input image for guidance method 1"
},
"guidance_method_2": {
"anyOf": [
{
"$ref": "#/components/schemas/ControlnetType"
},
{
"type": "null"
}
],
"description": "Guidance method 2",
"examples": [
"controlnet_canny",
"controlnet_depth"
]
},
"guidance_method_2_scale": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Guidance Method 2 Scale",
"description": "Impact of second guidance method"
},
"guidance_method_2_image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Guidance Method 2 Image Url",
"description": "URL of the image to use for guidance method 2",
"examples": [
"https://images.pexels.com/photos/33217722/pexels-photo-33217722.jpeg"
]
},
"guidance_method_2_image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Guidance Method 2 Image File",
"description": "Base64 encoded input image for guidance method 2"
},
"image_prompt_mode": {
"anyOf": [
{
"$ref": "#/components/schemas/ImagePromptMode"
},
{
"type": "null"
}
],
"description": "Image prompt mode",
"examples": [
"regular",
"style_only"
]
},
"image_prompt_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Image Prompt File",
"description": "Base64 encoded input image for image prompt"
},
"image_prompt_urls": {
"anyOf": [
{
"items": {
"type": "string",
"minLength": 1,
"format": "uri"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Image Prompt Urls",
"description": "URLs of the images to use for image prompt",
"examples": [
"https://images.pexels.com/photos/31448898/pexels-photo-31448898.jpeg",
"https://images.pexels.com/photos/33017020/pexels-photo-33017020.jpeg"
]
},
"image_prompt_scale": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Image Prompt Scale",
"description": "Scale of the image prompt"
}
},
"type": "object",
"required": [
"prompt"
],
"title": "BriaGenerateImageRequest",
"description": "Request model for BRIA image generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/generation/generate-image-fast¶
Bria Generate Image Fast
Description
Generate images quickly using BRIA's fast model.
Args:
- bria_model_version: Model version to use (e.g. "2.3").
- prompt: Text description of the desired image (English only).
- num_results: Number of images to generate. Use 1 when using guidance methods. Maximum value is 4.
- aspect_ratio: Image aspect ratio.
- sync: If True, wait for results. If False, return URLs immediately.
- steps_num: Number of refinement iterations (4-10).
- prompt_enhancement: Use LLama 3 to enhance prompt.
- seed (optional): Seed for reproducible results.
- medium (optional): Output medium type ("photography" or "art").
- guidance_method_1 (optional): First guidance method type. Supported guidance methods are: "controlnet_canny", "controlnet_depth", "controlnet_recoloring", "controlnet_color_grid".
- guidance_method_1_scale (optional): Impact of first guidance method (0.0-1.0).
- guidance_method_1_image_file (optional): Base64 encoded image for first guidance method. Required if guidance_method_1 is specified.
- guidance_method_1_image_url (optional): URL of image for first guidance method. Required if guidance_method_1 is specified.
- guidance_method_2 (optional): Second guidance method type. Supported guidance methods are: "controlnet_canny", "controlnet_depth", "controlnet_recoloring", "controlnet_color_grid".
- guidance_method_2_scale (optional): Impact of second guidance method (0.0-1.0).
- guidance_method_2_image_file (optional): Base64 encoded image for second guidance method. Required if guidance_method_2 is specified.
- guidance_method_2_image_url (optional): URL of image for second guidance method. Required if guidance_method_2 is specified.
- image_prompt_mode (optional): IP-Adapter mode. Supported modes are : "regular", "style_only".
- image_prompt_file (optional): Base64 encoded image for IP-Adapter.
- image_prompt_urls (optional): List of image URLs for IP-Adapter.
- image_prompt_scale (optional): Impact of IP-Adapter (0.0-1.0).
- access_token: API key for authentication.
- bria_client: BRIA API client.
Returns: Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"bria_model_version": "string",
"prompt": "string",
"num_results": 0,
"aspect_ratio": "1:1",
"sync": true,
"steps_num": 0,
"prompt_enhancement": true,
"enhance_image": true,
"prompt_content_moderation": true,
"content_moderation": true,
"ip_signal": true,
"seed": null,
"medium": null,
"guidance_method_1": null,
"guidance_method_1_scale": null,
"guidance_method_1_image_url": null,
"guidance_method_1_image_file": null,
"guidance_method_2": null,
"guidance_method_2_scale": null,
"guidance_method_2_image_url": null,
"guidance_method_2_image_file": null,
"image_prompt_mode": null,
"image_prompt_file": null,
"image_prompt_urls": null,
"image_prompt_scale": null
}
Schema of the request body
{
"properties": {
"bria_model_version": {
"type": "string",
"const": "2.3",
"title": "Bria Model Version",
"description": "BRIA model version to use",
"default": "2.3"
},
"prompt": {
"type": "string",
"minLength": 3,
"title": "Prompt",
"description": "Text description of the desired image (English only).",
"examples": [
"A mountain landscape with a lake",
"A cozy coffee shop interior",
"Professional headshot of a business person"
]
},
"num_results": {
"type": "integer",
"maximum": 4.0,
"minimum": 1.0,
"title": "Num Results",
"description": "Number of images to generate",
"default": 1
},
"aspect_ratio": {
"type": "string",
"enum": [
"1:1",
"2:3",
"3:2",
"3:4",
"4:3",
"16:9",
"9:16",
"4:5",
"5:4"
],
"title": "Aspect Ratio",
"description": "Image aspect ratio",
"default": "1:1"
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results. If False, return URLs immediately",
"default": true
},
"steps_num": {
"type": "integer",
"maximum": 10.0,
"minimum": 4.0,
"title": "Steps Num",
"description": "Number of refinement iterations",
"default": 8
},
"prompt_enhancement": {
"type": "boolean",
"title": "Prompt Enhancement",
"description": "Use LLama 3 to enhance prompt",
"default": false
},
"enhance_image": {
"type": "boolean",
"title": "Enhance Image",
"description": "Generates images with richer details, sharper textures, and enhanced clarity",
"default": false
},
"prompt_content_moderation": {
"type": "boolean",
"title": "Prompt Content Moderation",
"description": "When enabled (default: true), the input prompt is scanned for NSFW or ethically restricted terms before image generation.",
"default": false
},
"content_moderation": {
"type": "boolean",
"title": "Content Moderation",
"description": "When enabled, applies content moderation to both input visuals and generated outputs.",
"default": false
},
"ip_signal": {
"type": "boolean",
"title": "Ip Signal",
"description": "When enabled, adds an IP signature to the generated images.",
"default": false
},
"seed": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Seed",
"description": "Seed for reproducible results"
},
"medium": {
"anyOf": [
{
"type": "string",
"enum": [
"photography",
"art"
]
},
{
"type": "null"
}
],
"title": "Medium",
"description": "Output medium type"
},
"guidance_method_1": {
"anyOf": [
{
"$ref": "#/components/schemas/ControlnetType"
},
{
"type": "null"
}
],
"description": "Guidance method 1",
"examples": [
"controlnet_canny",
"controlnet_depth"
]
},
"guidance_method_1_scale": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Guidance Method 1 Scale",
"description": "Impact of first guidance method"
},
"guidance_method_1_image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Guidance Method 1 Image Url",
"description": "URL of the image to use for guidance method 1",
"examples": [
"https://images.pexels.com/photos/31976103/pexels-photo-31976103.jpeg"
]
},
"guidance_method_1_image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Guidance Method 1 Image File",
"description": "Base64 encoded input image for guidance method 1"
},
"guidance_method_2": {
"anyOf": [
{
"$ref": "#/components/schemas/ControlnetType"
},
{
"type": "null"
}
],
"description": "Guidance method 2",
"examples": [
"controlnet_canny",
"controlnet_depth"
]
},
"guidance_method_2_scale": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Guidance Method 2 Scale",
"description": "Impact of second guidance method"
},
"guidance_method_2_image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Guidance Method 2 Image Url",
"description": "URL of the image to use for guidance method 2",
"examples": [
"https://images.pexels.com/photos/33217722/pexels-photo-33217722.jpeg"
]
},
"guidance_method_2_image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Guidance Method 2 Image File",
"description": "Base64 encoded input image for guidance method 2"
},
"image_prompt_mode": {
"anyOf": [
{
"$ref": "#/components/schemas/ImagePromptMode"
},
{
"type": "null"
}
],
"description": "Image prompt mode",
"examples": [
"regular",
"style_only"
]
},
"image_prompt_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Image Prompt File",
"description": "Base64 encoded input image for image prompt"
},
"image_prompt_urls": {
"anyOf": [
{
"items": {
"type": "string",
"minLength": 1,
"format": "uri"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Image Prompt Urls",
"description": "URLs of the images to use for image prompt",
"examples": [
"https://images.pexels.com/photos/31448898/pexels-photo-31448898.jpeg",
"https://images.pexels.com/photos/33017020/pexels-photo-33017020.jpeg"
]
},
"image_prompt_scale": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Image Prompt Scale",
"description": "Scale of the image prompt"
}
},
"type": "object",
"required": [
"prompt"
],
"title": "BriaGenerateImageFastRequest"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/generation/generate-image-hd¶
Bria Generate Image Hd
Description
Generate high-resolution images using BRIA's HD model.
Args:
- bria_model_version: Model version to use (e.g. "2.2").
- prompt: Text description of the desired image (English only).
- num_results: Number of images to generate. Maximum value is 4.
- aspect_ratio: Image aspect ratio.
- sync: If True, wait for results. If False, return URLs immediately.
- steps_num: Number of refinement iterations (20-50).
- text_guidance_scale: Text adherence strength (1-10).
- prompt_enhancement: Use LLama 3 to enhance prompt.
- seed (optional): Seed for reproducible results.
- negative_prompt (optional): Elements to exclude from generation.
- medium (optional): Output medium type ("photography" or "art").
- access_token: API key for authentication.
- bria_client: BRIA API client.
Returns: Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"bria_model_version": "string",
"prompt": "string",
"num_results": 0,
"aspect_ratio": "1:1",
"sync": true,
"steps_num": 0,
"text_guidance_scale": 10.12,
"prompt_enhancement": true,
"enhance_image": true,
"content_moderation": true,
"ip_signal": true,
"seed": null,
"negative_prompt": null,
"medium": null
}
Schema of the request body
{
"properties": {
"bria_model_version": {
"type": "string",
"const": "2.2",
"title": "Bria Model Version",
"description": "BRIA model version to use",
"default": "2.2"
},
"prompt": {
"type": "string",
"minLength": 4,
"title": "Prompt",
"description": "Text description of the desired image (English only).",
"examples": [
"A mountain landscape with a lake",
"A cozy coffee shop interior",
"Professional headshot of a business person"
]
},
"num_results": {
"type": "integer",
"maximum": 4.0,
"minimum": 1.0,
"title": "Num Results",
"description": "Number of images to generate",
"default": 1
},
"aspect_ratio": {
"type": "string",
"enum": [
"1:1",
"2:3",
"3:2",
"3:4",
"4:3",
"16:9",
"9:16",
"4:5",
"5:4"
],
"title": "Aspect Ratio",
"description": "Image aspect ratio",
"default": "1:1"
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results",
"default": true
},
"steps_num": {
"type": "integer",
"maximum": 50.0,
"minimum": 20.0,
"title": "Steps Num",
"description": "Number of refinement iterations",
"default": 30
},
"text_guidance_scale": {
"type": "number",
"maximum": 10.0,
"minimum": 1.0,
"title": "Text Guidance Scale",
"description": "Text adherence strength",
"default": 5.0
},
"prompt_enhancement": {
"type": "boolean",
"title": "Prompt Enhancement",
"description": "Use LLama 3 to enhance prompt",
"default": false
},
"enhance_image": {
"type": "boolean",
"title": "Enhance Image",
"description": "Generates images with richer details, sharper textures, and enhanced clarity",
"default": false
},
"content_moderation": {
"type": "boolean",
"title": "Content Moderation",
"description": "When enabled, applies content moderation to both input visuals and generated outputs.",
"default": false
},
"ip_signal": {
"type": "boolean",
"title": "Ip Signal",
"description": "When enabled, adds an IP signature to the generated images.",
"default": false
},
"seed": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Seed",
"description": "Seed for reproducible results"
},
"negative_prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Negative Prompt",
"description": "Elements to exclude",
"examples": [
"text",
"logo",
"watermark",
"background"
]
},
"medium": {
"anyOf": [
{
"type": "string",
"enum": [
"photography",
"art"
]
},
{
"type": "null"
}
],
"title": "Medium",
"description": "Output medium type"
}
},
"type": "object",
"required": [
"prompt"
],
"title": "BriaGenerateImageHDRequest"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/generation/generate-vector-base¶
Bria Generate Vector Base
Description
Generate high-quality vector graphics using BRIA's base model (Beta). This endpoint provides vector graphic generation that is highly customizable and supports various guidance methods.
Args:
- bria_model_version: Model version to use (e.g. "2.3").
- prompt: Text description of desired vector graphic (English only).
- num_results: Number of images to generate. Use 1 when using guidance methods. Maximum value is 4.
- aspect_ratio: Image aspect ratio.
- sync: If True, wait for results. If False, return URLs immediately.
- steps_num: Number of refinement iterations (20-50).
- text_guidance_scale: Text adherence strength (1-10).
- seed (optional): Seed for reproducible results.
- negative_prompt (optional): Elements to exclude from generation.
- guidance_method_1 (optional): First guidance method type. Supported guidance methods are: "controlnet_canny", "controlnet_depth", "controlnet_recoloring", "controlnet_color_grid".
- guidance_method_1_scale (optional): Impact of first guidance method (0.0-1.0).
- guidance_method_1_image_file (optional): Base64 encoded image for first guidance method. Required if guidance_method_1 is specified.
- guidance_method_1_image_url (optional): URL of image for first guidance method. Required if guidance_method_1 is specified.
- guidance_method_2 (optional): Second guidance method type. Supported guidance methods are: "controlnet_canny", "controlnet_depth", "controlnet_recoloring", "controlnet_color_grid".
- guidance_method_2_scale (optional): Impact of second guidance method (0.0-1.0).
- guidance_method_2_image_file (optional): Base64 encoded image for second guidance method. Required if guidance_method_2 is specified.
- image_prompt_mode (optional): IP-Adapter mode. Supported modes are : "regular", "style_only".
- image_prompt_file (optional): Base64 encoded image for IP-Adapter.
- image_prompt_urls (optional): List of image URLs for IP-Adapter.
- image_prompt_scale (optional): Impact of IP-Adapter (0.0-1.0).
- access_token: API key for authentication.
- bria_client: BRIA API client.
Returns: Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"bria_model_version": "2.3",
"prompt": "string",
"aspect_ratio": "1:1",
"num_results": 0,
"sync": true,
"steps_num": 0,
"text_guidance_scale": 10.12,
"prompt_content_moderation": true,
"content_moderation": true,
"ip_signal": true,
"seed": null,
"negative_prompt": null,
"guidance_method_1": null,
"guidance_method_1_scale": null,
"guidance_method_1_image_url": null,
"guidance_method_1_image_file": null,
"guidance_method_2": null,
"guidance_method_2_scale": null,
"guidance_method_2_image_url": null,
"guidance_method_2_image_file": null,
"image_prompt_mode": null,
"image_prompt_file": null,
"image_prompt_urls": null,
"image_prompt_scale": null
}
Schema of the request body
{
"properties": {
"bria_model_version": {
"type": "string",
"enum": [
"2.3",
"3.2"
],
"title": "Bria Model Version",
"description": "BRIA model version to use",
"default": "3.2"
},
"prompt": {
"type": "string",
"minLength": 4,
"title": "Prompt",
"description": "Text description of desired vector graphic (English only)",
"examples": [
"A fox in the mountains",
"A man in the city"
]
},
"aspect_ratio": {
"type": "string",
"enum": [
"1:1",
"2:3",
"3:2",
"3:4",
"4:3",
"16:9",
"9:16",
"4:5",
"5:4"
],
"title": "Aspect Ratio",
"description": "Image aspect ratio",
"default": "1:1"
},
"num_results": {
"type": "integer",
"maximum": 4.0,
"minimum": 1.0,
"title": "Num Results",
"description": "Number of images to generate",
"default": 1
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results",
"default": true
},
"steps_num": {
"type": "integer",
"maximum": 50.0,
"minimum": 20.0,
"title": "Steps Num",
"description": "Number of refinement iterations",
"default": 30
},
"text_guidance_scale": {
"type": "number",
"maximum": 10.0,
"minimum": 1.0,
"title": "Text Guidance Scale",
"description": "Text adherence strength",
"default": 5.0
},
"prompt_content_moderation": {
"type": "boolean",
"title": "Prompt Content Moderation",
"description": "When enabled, applies content moderation to both input visuals and generated outputs.",
"default": false
},
"content_moderation": {
"type": "boolean",
"title": "Content Moderation",
"description": "When enabled, applies content moderation to both input visuals and generated outputs.",
"default": false
},
"ip_signal": {
"type": "boolean",
"title": "Ip Signal",
"description": "When enabled, adds an IP signature to the generated images.",
"default": false
},
"seed": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Seed",
"description": "Seed for reproducible results"
},
"negative_prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Negative Prompt",
"description": "Elements to exclude",
"examples": [
"text",
"logo",
"watermark",
"background"
]
},
"guidance_method_1": {
"anyOf": [
{
"$ref": "#/components/schemas/ControlnetType"
},
{
"type": "null"
}
],
"description": "Guidance method 1",
"examples": [
"controlnet_canny",
"controlnet_depth"
]
},
"guidance_method_1_scale": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Guidance Method 1 Scale",
"description": "Impact of first guidance method"
},
"guidance_method_1_image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Guidance Method 1 Image Url",
"description": "URL of the image to use for guidance method 1",
"examples": [
"https://images.pexels.com/photos/31976103/pexels-photo-31976103.jpeg"
]
},
"guidance_method_1_image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Guidance Method 1 Image File",
"description": "Base64 encoded input image for guidance method 1"
},
"guidance_method_2": {
"anyOf": [
{
"$ref": "#/components/schemas/ControlnetType"
},
{
"type": "null"
}
],
"description": "Guidance method 2",
"examples": [
"controlnet_canny",
"controlnet_depth"
]
},
"guidance_method_2_scale": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Guidance Method 2 Scale",
"description": "Impact of second guidance method"
},
"guidance_method_2_image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Guidance Method 2 Image Url",
"description": "URL of the image to use for guidance method 2",
"examples": [
"https://images.pexels.com/photos/33217722/pexels-photo-33217722.jpeg"
]
},
"guidance_method_2_image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Guidance Method 2 Image File",
"description": "Base64 encoded input image for guidance method 2"
},
"image_prompt_mode": {
"anyOf": [
{
"$ref": "#/components/schemas/ImagePromptMode"
},
{
"type": "null"
}
],
"description": "Image prompt mode",
"examples": [
"regular",
"style_only"
]
},
"image_prompt_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Image Prompt File",
"description": "Base64 encoded input image for image prompt"
},
"image_prompt_urls": {
"anyOf": [
{
"items": {
"type": "string",
"minLength": 1,
"format": "uri"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Image Prompt Urls",
"description": "URLs of the images to use for image prompt",
"examples": [
"https://images.pexels.com/photos/31448898/pexels-photo-31448898.jpeg",
"https://images.pexels.com/photos/33017020/pexels-photo-33017020.jpeg"
]
},
"image_prompt_scale": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Image Prompt Scale",
"description": "Scale of the image prompt"
}
},
"type": "object",
"required": [
"prompt"
],
"title": "BriaGenerateVectorBaseRequest"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/generation/generate-vector-fast¶
Bria Vector Generation Fast
Description
Generate vector graphics quickly using BRIA's fast model (Beta). This endpoint provides rapid vector graphic generation without compromising quality. Supports the same guidance methods as the base model for enhanced control.
Args:
- bria_model_version: Model version to use (e.g. "2.3").
- prompt: Text description of desired vector graphic (English only).
- num_results: Number of images to generate. Use 1 when using guidance methods. Maximum value is 4.
- aspect_ratio: Image aspect ratio.
- sync: If True, wait for results. If False, return URLs immediately.
- steps_num: Number of refinement iterations (4-10).
- seed (optional): Seed for reproducible results.
- guidance_method_1 (optional): First guidance method type. Supported guidance methods are: "controlnet_canny", "controlnet_depth", "controlnet_recoloring", "controlnet_color_grid".
- guidance_method_1_scale (optional): Impact of first guidance method (0.0-1.0).
- guidance_method_1_image_file (optional): Base64 encoded image for first guidance method. Required if guidance_method_1 is specified.
- guidance_method_2 (optional): Second guidance method type. Supported guidance methods are: "controlnet_canny", "controlnet_depth", "controlnet_recoloring", "controlnet_color_grid".
- guidance_method_2_scale (optional): Impact of second guidance method (0.0-1.0).
- guidance_method_2_image_file (optional): Base64 encoded image for second guidance method. Required if guidance_method_2 is specified.
- guidance_method_2_image_url (optional): URL of image for second guidance method. Required if guidance_method_2 is specified.
- image_prompt_mode (optional): IP-Adapter mode. Supported modes are : "regular", "style_only".
- image_prompt_file (optional): Base64 encoded image for IP-Adapter.
- image_prompt_urls (optional): List of image URLs for IP-Adapter.
- image_prompt_scale (optional): Impact of IP-Adapter (0.0-1.0).
- access_token: API key for authentication.
- bria_client: BRIA API client.
Returns: Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"bria_model_version": "string",
"prompt": "string",
"aspect_ratio": "1:1",
"num_results": 0,
"sync": true,
"steps_num": 0,
"prompt_content_moderation": true,
"content_moderation": true,
"ip_signal": true,
"seed": null,
"guidance_method_1": null,
"guidance_method_1_scale": null,
"guidance_method_1_image_url": null,
"guidance_method_1_image_file": null,
"guidance_method_2": null,
"guidance_method_2_scale": null,
"guidance_method_2_image_url": null,
"guidance_method_2_image_file": null,
"image_prompt_mode": null,
"image_prompt_file": null,
"image_prompt_urls": null,
"image_prompt_scale": null
}
Schema of the request body
{
"properties": {
"bria_model_version": {
"type": "string",
"const": "2.3",
"title": "Bria Model Version",
"description": "BRIA model version to use",
"default": "2.3"
},
"prompt": {
"type": "string",
"minLength": 4,
"title": "Prompt",
"description": "Text description of desired vector graphic (English only)",
"examples": [
"A fox in the mountains",
"A man in the city"
]
},
"aspect_ratio": {
"type": "string",
"enum": [
"1:1",
"2:3",
"3:2",
"3:4",
"4:3",
"16:9",
"9:16",
"4:5",
"5:4"
],
"title": "Aspect Ratio",
"description": "Image aspect ratio",
"default": "1:1"
},
"num_results": {
"type": "integer",
"maximum": 4.0,
"minimum": 1.0,
"title": "Num Results",
"description": "Number of images to generate",
"default": 1
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results",
"default": true
},
"steps_num": {
"type": "integer",
"maximum": 10.0,
"minimum": 4.0,
"title": "Steps Num",
"description": "Number of refinement iterations",
"default": 8
},
"prompt_content_moderation": {
"type": "boolean",
"title": "Prompt Content Moderation",
"description": "When enabled, applies content moderation to both input visuals and generated outputs.",
"default": false
},
"content_moderation": {
"type": "boolean",
"title": "Content Moderation",
"description": "When enabled, applies content moderation to both input visuals and generated outputs.",
"default": false
},
"ip_signal": {
"type": "boolean",
"title": "Ip Signal",
"description": "When enabled, adds an IP signature to the generated images.",
"default": false
},
"seed": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Seed",
"description": "Seed for reproducible results"
},
"guidance_method_1": {
"anyOf": [
{
"$ref": "#/components/schemas/ControlnetType"
},
{
"type": "null"
}
],
"description": "Guidance method 1",
"examples": [
"controlnet_canny",
"controlnet_depth"
]
},
"guidance_method_1_scale": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Guidance Method 1 Scale",
"description": "Impact of first guidance method"
},
"guidance_method_1_image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Guidance Method 1 Image Url",
"description": "URL of the image to use for guidance method 1",
"examples": [
"https://images.pexels.com/photos/31976103/pexels-photo-31976103.jpeg"
]
},
"guidance_method_1_image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Guidance Method 1 Image File",
"description": "Base64 encoded input image for guidance method 1"
},
"guidance_method_2": {
"anyOf": [
{
"$ref": "#/components/schemas/ControlnetType"
},
{
"type": "null"
}
],
"description": "Guidance method 2",
"examples": [
"controlnet_canny",
"controlnet_depth"
]
},
"guidance_method_2_scale": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Guidance Method 2 Scale",
"description": "Impact of second guidance method"
},
"guidance_method_2_image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Guidance Method 2 Image Url",
"description": "URL of the image to use for guidance method 2",
"examples": [
"https://images.pexels.com/photos/33217722/pexels-photo-33217722.jpeg"
]
},
"guidance_method_2_image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Guidance Method 2 Image File",
"description": "Base64 encoded input image for guidance method 2"
},
"image_prompt_mode": {
"anyOf": [
{
"$ref": "#/components/schemas/ImagePromptMode"
},
{
"type": "null"
}
],
"description": "Image prompt mode",
"examples": [
"regular",
"style_only"
]
},
"image_prompt_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Image Prompt File",
"description": "Base64 encoded input image for image prompt"
},
"image_prompt_urls": {
"anyOf": [
{
"items": {
"type": "string",
"minLength": 1,
"format": "uri"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Image Prompt Urls",
"description": "URLs of the images to use for image prompt",
"examples": [
"https://images.pexels.com/photos/31448898/pexels-photo-31448898.jpeg",
"https://images.pexels.com/photos/33017020/pexels-photo-33017020.jpeg"
]
},
"image_prompt_scale": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Image Prompt Scale",
"description": "Scale of the image prompt"
}
},
"type": "object",
"required": [
"prompt"
],
"title": "BriaGenerateVectorFastRequest"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/generation/generate-variation¶
Bria Generate Variation
Description
Guides image generation using both prompts and a reference image, maintaining the original structure while applying new styles. This method allows for controlled image generation by using an input image's structure and depth as a reference, while incorporating new materials, colors, and textures based on the provided prompt.
Args:
- prompt: Text description of desired output image.
- num_results : Number of images to generate (1-4). Only 1 supported when fast=False. Maximum value is 4.
- sync: If True, wait for results. If False, return URLs immediately. Recommended False when fast=False.
- fast: Use fast generation mode for speed/quality balance. Regular mode used when False.
- steps_num: Number of refinement iterations. Fast mode: 4-20, default
- Regular mode: 20-50, default 30.
- seed (optional): Seed for reproducible results.
- image_url (optional): URL of reference image. Takes precedence over image_file. Max 12MB. Formats: jpeg, jpg, png, webp.
- image_file (optional): Base64 encoded reference image. Used if image_url not provided. Max 12MB. Formats: jpeg, jpg, png, webp.
- ref_image_influence (float, optional): Weight of reference image in generation (0-1). Higher values mean stronger adherence to reference.
- tailored_model_id (optional): ID of custom trained model to use. 'Max' training version models not supported.
- tailored_model_influence (float, optional): Weight of tailored model in generation (0-1). Only used with tailored_model_id. If used, default is 0.5.
- include_generation_prefix (optional): Auto-prepend model's training prefix to prompt. Only relevant with tailored models. Set False to use custom prefix.
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Returns: Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"prompt": "string",
"num_results": 0,
"sync": true,
"fast": true,
"steps_num": 0,
"ref_image_influence": 10.12,
"include_generation_prefix": true,
"enhance_image": true,
"prompt_content_moderation": true,
"content_moderation": true,
"ip_signal": true,
"seed": null,
"image_url": null,
"image_file": null,
"tailored_model_id": null,
"tailored_model_influence": null
}
Schema of the request body
{
"properties": {
"prompt": {
"type": "string",
"minLength": 4,
"title": "Prompt",
"description": "Text description of desired output image.",
"examples": [
"Beautiful sunset colors",
"Black and white vintage photo"
]
},
"num_results": {
"type": "integer",
"maximum": 4.0,
"minimum": 1.0,
"title": "Num Results",
"description": "Number of images to generate",
"default": 1
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results. If False, return URLs immediately",
"default": true
},
"fast": {
"type": "boolean",
"title": "Fast",
"description": "Use fast generation mode for speed/quality balance",
"default": true
},
"steps_num": {
"type": "integer",
"maximum": 50.0,
"minimum": 20.0,
"title": "Steps Num",
"description": "Number of refinement iterations",
"default": 30
},
"ref_image_influence": {
"type": "number",
"maximum": 1.0,
"minimum": 0.0,
"title": "Ref Image Influence",
"description": "Weight of reference image in generation",
"default": 0.75
},
"include_generation_prefix": {
"type": "boolean",
"title": "Include Generation Prefix",
"description": "Auto-prepend Custom Model's training prefix to prompt",
"default": true
},
"enhance_image": {
"type": "boolean",
"title": "Enhance Image",
"description": "Generates images with richer details, sharper textures, and enhanced clarity",
"default": false
},
"prompt_content_moderation": {
"type": "boolean",
"title": "Prompt Content Moderation",
"description": "When enabled (default: true), the input prompt is scanned for NSFW or ethically restricted terms before image generation.",
"default": false
},
"content_moderation": {
"type": "boolean",
"title": "Content Moderation",
"description": "When enabled, applies content moderation to both input visuals and generated outputs.",
"default": false
},
"ip_signal": {
"type": "boolean",
"title": "Ip Signal",
"description": "When enabled, adds an IP signature to the generated images.",
"default": false
},
"seed": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Seed",
"description": "Seed for reproducible results"
},
"image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Image Url",
"description": "URL of reference image",
"examples": [
"https://images.pexels.com/photos/31976103/pexels-photo-31976103.jpeg"
]
},
"image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Image File",
"description": "Base64 encoded reference image"
},
"tailored_model_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Tailored Model Id",
"description": "ID of Custom Model trained model to use"
},
"tailored_model_influence": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Tailored Model Influence",
"description": "Weight of tailored model in generation"
}
},
"type": "object",
"required": [
"prompt"
],
"title": "BriaGenerateVariationRequest"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria-lora/image/generation/generate-image¶
Generate Images
Description
Generate images using a specified model.
Args:
- model_id: ID of the model to use for generation
- prompt: Text prompt for image generation
- num_results: Number of images to generate (default: 1)
- seed: Random seed for reproducibility (optional)
- sync: Whether to perform synchronous generation (default: False)
- fast: Whether to use fast generation mode (default: False) At the moment, tailored models trained using the 'Max'/3.2 training version, do not support fast generation.
- steps_num: Number of steps for the generation process (default: 20)
- model_influence: Influence of the model on the generation (default: 1.0)
- include_generation_prefix: Whether to include a prefix in the generated images (default: False)
Returns: - JSONResponse: Response containing the generated images or an error message
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"model_id": "string",
"prompt": "string",
"aspect_ratio": "1:1",
"num_results": 0,
"sync": true,
"fast": true,
"steps_num": null,
"model_influence": null,
"include_generation_prefix": true,
"seed": null
}
Schema of the request body
{
"properties": {
"model_id": {
"type": "string",
"title": "Model Id",
"description": "ID of the Lora model to use"
},
"prompt": {
"type": "string",
"minLength": 4,
"title": "Prompt",
"description": "Text prompt for generation (English only)",
"examples": [
"A mountain landscape with a lake",
"A cozy coffee shop interior"
]
},
"aspect_ratio": {
"type": "string",
"enum": [
"1:1",
"2:3",
"3:2",
"3:4",
"4:3",
"16:9",
"9:16",
"4:5",
"5:4"
],
"title": "Aspect Ratio",
"description": "Image aspect ratio",
"default": "1:1"
},
"num_results": {
"type": "integer",
"maximum": 4.0,
"minimum": 1.0,
"title": "Num Results",
"description": "Number of images to generate",
"default": 1
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results",
"default": true
},
"fast": {
"type": "boolean",
"title": "Fast",
"description": "Use fast generation mode for speed/quality balance",
"default": false
},
"steps_num": {
"anyOf": [
{
"type": "integer",
"maximum": 50.0,
"minimum": 4.0
},
{
"type": "null"
}
],
"title": "Steps Num",
"description": "Number of refinement iterations. When fast=false, the default value is 30, the minimum is 20 and the maximum is 50"
},
"model_influence": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Model Influence",
"description": "Influence of the Lora model"
},
"include_generation_prefix": {
"type": "boolean",
"title": "Include Generation Prefix",
"description": "Auto-prepend Custom Model's training prefix to prompt",
"default": true
},
"seed": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Seed",
"description": "Seed for reproducible results"
}
},
"type": "object",
"required": [
"model_id",
"prompt"
],
"title": "BriaLoraGenerateImagesRequest",
"description": "Request model for generating images with Bria Lora (BRIA API v2).\n\nThis model only includes fields supported by the generate_images API method.\nFor advanced features like guidance methods, use BriaLoraGenerateVectorRequest."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria-lora/image/generation/generate-vector¶
Generate Vector
Description
Generate a vector using a specified model.
Args:
- model_id: ID of the model to use for vector generation
- prompt: Text prompt for vector generation
- num_results: Number of vectors to generate (default: 1)
- seed: Random seed for reproducibility (optional)
- sync: Whether to perform synchronous generation (default: True)
- fast: Whether to use fast generation mode (default: True) At the moment, tailored models trained using the 'Max'/3.2 training version, do not support fast generation. Therefore, steps_num minimum is 20.
- steps_num: Number of steps for the generation process (optional)
- model_influence: Influence of the model on the generation (optional)
- include_generation_prefix: Whether to include a prefix in the generated vector (default: True)
Returns: - JSONResponse: Response containing the generated vector or an error message
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"bria_model_version": "2.3",
"model_id": "string",
"prompt": "string",
"aspect_ratio": "1:1",
"num_results": 0,
"sync": true,
"steps_num": null,
"text_guidance_scale": null,
"prompt_content_moderation": true,
"content_moderation": true,
"seed": null,
"negative_prompt": null,
"model_influence": null,
"include_generation_prefix": true,
"guidance_method_1": null,
"guidance_method_1_scale": null,
"guidance_method_1_image_url": null,
"guidance_method_1_image_file": null,
"guidance_method_2": null,
"guidance_method_2_scale": null,
"guidance_method_2_image_url": null,
"guidance_method_2_image_file": null,
"image_prompt_mode": null,
"image_prompt_file": null,
"image_prompt_urls": null,
"image_prompt_scale": null
}
Schema of the request body
{
"properties": {
"bria_model_version": {
"type": "string",
"enum": [
"2.3",
"3.2"
],
"title": "Bria Model Version",
"description": "BRIA model version to use",
"default": "3.2"
},
"model_id": {
"type": "string",
"title": "Model Id",
"description": "ID of the Lora model to use"
},
"prompt": {
"type": "string",
"minLength": 4,
"title": "Prompt",
"description": "Text description of desired vector graphic (English only)",
"examples": [
"A fox in the mountains",
"A man in the city"
]
},
"aspect_ratio": {
"type": "string",
"enum": [
"1:1",
"2:3",
"3:2",
"3:4",
"4:3",
"16:9",
"9:16",
"4:5",
"5:4"
],
"title": "Aspect Ratio",
"description": "Image aspect ratio",
"default": "1:1"
},
"num_results": {
"type": "integer",
"maximum": 4.0,
"minimum": 1.0,
"title": "Num Results",
"description": "Number of vectors to generate",
"default": 1
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results",
"default": true
},
"steps_num": {
"anyOf": [
{
"type": "integer",
"maximum": 50.0,
"minimum": 20.0
},
{
"type": "null"
}
],
"title": "Steps Num",
"description": "Number of refinement iterations"
},
"text_guidance_scale": {
"anyOf": [
{
"type": "number",
"maximum": 10.0,
"minimum": 1.0
},
{
"type": "null"
}
],
"title": "Text Guidance Scale",
"description": "Text adherence strength"
},
"prompt_content_moderation": {
"type": "boolean",
"title": "Prompt Content Moderation",
"description": "When enabled, the input prompt is scanned for NSFW or ethically restricted terms before image generation.",
"default": false
},
"content_moderation": {
"type": "boolean",
"title": "Content Moderation",
"description": "When enabled, applies content moderation to both input visuals and generated outputs.",
"default": false
},
"seed": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Seed",
"description": "Seed for reproducible results"
},
"negative_prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Negative Prompt",
"description": "Elements to exclude",
"examples": [
"text",
"logo",
"watermark",
"background"
]
},
"model_influence": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Model Influence",
"description": "Influence of the Lora model"
},
"include_generation_prefix": {
"type": "boolean",
"title": "Include Generation Prefix",
"description": "Auto-prepend Custom Model's training prefix to prompt",
"default": true
},
"guidance_method_1": {
"anyOf": [
{
"$ref": "#/components/schemas/ControlnetType"
},
{
"type": "null"
}
],
"description": "Guidance method 1",
"examples": [
"controlnet_canny",
"controlnet_depth"
]
},
"guidance_method_1_scale": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Guidance Method 1 Scale",
"description": "Impact of first guidance method"
},
"guidance_method_1_image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Guidance Method 1 Image Url",
"description": "URL of the image to use for guidance method 1",
"examples": [
"https://images.pexels.com/photos/31976103/pexels-photo-31976103.jpeg"
]
},
"guidance_method_1_image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Guidance Method 1 Image File",
"description": "Base64 encoded input image for guidance method 1"
},
"guidance_method_2": {
"anyOf": [
{
"$ref": "#/components/schemas/ControlnetType"
},
{
"type": "null"
}
],
"description": "Guidance method 2",
"examples": [
"controlnet_canny",
"controlnet_depth"
]
},
"guidance_method_2_scale": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Guidance Method 2 Scale",
"description": "Impact of second guidance method"
},
"guidance_method_2_image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Guidance Method 2 Image Url",
"description": "URL of the image to use for guidance method 2",
"examples": [
"https://images.pexels.com/photos/33217722/pexels-photo-33217722.jpeg"
]
},
"guidance_method_2_image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Guidance Method 2 Image File",
"description": "Base64 encoded input image for guidance method 2"
},
"image_prompt_mode": {
"anyOf": [
{
"$ref": "#/components/schemas/ImagePromptMode"
},
{
"type": "null"
}
],
"description": "Image prompt mode",
"examples": [
"regular",
"style_only"
]
},
"image_prompt_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Image Prompt File",
"description": "Base64 encoded input image for image prompt"
},
"image_prompt_urls": {
"anyOf": [
{
"items": {
"type": "string",
"minLength": 1,
"format": "uri"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Image Prompt Urls",
"description": "URLs of the images to use for image prompt",
"examples": [
"https://images.pexels.com/photos/31448898/pexels-photo-31448898.jpeg",
"https://images.pexels.com/photos/33017020/pexels-photo-33017020.jpeg"
]
},
"image_prompt_scale": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Image Prompt Scale",
"description": "Scale of the image prompt"
}
},
"type": "object",
"required": [
"model_id",
"prompt"
],
"title": "BriaLoraGenerateVectorRequest",
"description": "Request model for generating vector graphics with Bria Lora (BRIA API v2)."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/google-vision/image/generation/generate-image¶
Imagen Generate Image With Prompt
Description
Generate images using Vertex AI Imagen.
Args:
- prompt : Image generation prompt.
- number_of_images (optional): Number of images to generate (1-4).
Defaults to 1.
- aspect_ratio (optional): Desired aspect ratio. Options:
- 1:1 (SQUARE): Square format
- 9:16 (PORTRAIT): Vertical portrait format
- 16:9 (LANDSCAPE): Horizontal landscape format
- 3:4 (PORTRAIT_STANDARD): Standard portrait format
- 4:3 (LANDSCAPE_STANDARD): Standard landscape format
- model_name (optional): Model to use:
- imagen-3.0-generate-002 (IMAGEN_3_STANDARD): Standard Imagen 3.0
model
- imagen-4.0-generate-preview-06-06 (IMAGEN_4_STANDARD): Standard
Imagen 4.0 model
- imagen-4.0-ultra-generate-preview-06-06 (IMAGEN_4_ULTRA): Ultra
high-quality Imagen 4.0 model
- imagen-4.0-fast-generate-preview-06-06 (IMAGEN_4_FAST): Fast Imagen
4.0 model
- use_fast_model (optional, bool): When enabled, uses the fast
generation model and ignores the model_name parameter.
- add_watermark (optional, bool): Whether to add a watermark to the
generated images.
- safety_filter_level (optional): Safety filtering level:
- BLOCK_LOW_AND_ABOVE (HIGH): Highest safety threshold
- BLOCK_MEDIUM_AND_ABOVE (MEDIUM): Medium safety threshold
- BLOCK_ONLY_HIGH (LOW): Reduced safety threshold
- person_generation (optional): Person generation control:
- ALLOW_ALL (ALL): Allow people of all ages
- ALLOW_ADULT (ADULT): Allow only adults
- DONT_ALLOW (NONE): Disable people/faces in generated images
Returns: - Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"model_name": null,
"prompt": "string",
"aspect_ratio": "1:1",
"number_of_images": 0,
"use_fast_model": true,
"add_watermark": true,
"safety_filter_level": "BLOCK_LOW_AND_ABOVE",
"person_generation": "DONT_ALLOW"
}
Schema of the request body
{
"properties": {
"model_name": {
"anyOf": [
{
"$ref": "#/components/schemas/ModelName"
},
{
"type": "null"
}
],
"description": "Imagen model to use",
"default": "imagen-4.0-fast-generate-preview-06-06"
},
"prompt": {
"type": "string",
"minLength": 3,
"title": "Prompt",
"description": "Text description of the desired image",
"default": "A beautiful sunset over mountains"
},
"aspect_ratio": {
"type": "string",
"enum": [
"1:1",
"9:16",
"16:9",
"3:4",
"4:3"
],
"title": "Aspect Ratio",
"description": "Desired aspect ratio",
"default": "1:1"
},
"number_of_images": {
"type": "integer",
"maximum": 4.0,
"minimum": 1.0,
"title": "Number Of Images",
"description": "Number of images to generate",
"default": 1
},
"use_fast_model": {
"type": "boolean",
"title": "Use Fast Model",
"description": "Use faster model variant when available",
"default": true
},
"add_watermark": {
"type": "boolean",
"title": "Add Watermark",
"description": "Add watermark to generated images",
"default": false
},
"safety_filter_level": {
"$ref": "#/components/schemas/SafetyFilterLevel",
"description": "Content safety filtering level",
"default": "BLOCK_MEDIUM_AND_ABOVE"
},
"person_generation": {
"$ref": "#/components/schemas/google__genai__types__PersonGeneration",
"description": "Person generation policy",
"default": "ALLOW_ALL"
}
},
"type": "object",
"title": "ImagenGenerateImageRequest",
"description": "Request model for Imagen image generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/google-vision/image/generation/generate-with-image-guidance¶
Imagen Generate With Image
Description
Generate images with image guidance (style or subject).
Args:
- guidance_type : Type of guidance ("style" or "subject").
- prompt : Generation prompt. For prompting guidelines see examples
style , subject.
- ref_image_1_url : URL of the first reference image.
- ref_image_1_description : Description of the first reference image, if
guidance_type is style, describe only the style of the reference image, if
guidance_type is subject, describe only the subject of the reference image.
- ref_image_2_url (optional): URL of the second reference image.
- ref_image_2_description (optional): Description of the second
reference image.
- subject_type (optional): Required when guidance_type is 'subject',
else leave empty. Type of subject:
- SUBJECT_TYPE_PERSON: Person subject type (portraits, etc.)
- SUBJECT_TYPE_ANIMAL: Animal subject type
- SUBJECT_TYPE_PRODUCT: Product subject type (for e-commerce, etc.)
- aspect_ratio (optional): Desired aspect ratio. Options:
- 1:1 (SQUARE): Square format
- 9:16 (PORTRAIT): Vertical portrait format
- 16:9 (LANDSCAPE): Horizontal landscape format
- 3:4 (PORTRAIT_STANDARD): Standard portrait format
- 4:3 (LANDSCAPE_STANDARD): Standard landscape format
- safety_filter_level (optional): Safety filtering level:
- BLOCK_LOW_AND_ABOVE (HIGH): Highest safety threshold
- BLOCK_MEDIUM_AND_ABOVE (MEDIUM): Medium safety threshold
- BLOCK_ONLY_HIGH (LOW): Reduced safety threshold
- person_generation (optional): Person generation control:
- ALLOW_ALL (ALL): Allow people of all ages
- ALLOW_ADULT (ADULT): Allow only adults
- DONT_ALLOW (NONE): Disable people/faces in generated images
Returns: - Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"guidance_type": "style",
"ref_image_1_url": "string",
"ref_image_1_description": null,
"ref_image_2_url": null,
"ref_image_2_description": null,
"subject_type": null,
"prompt": null,
"aspect_ratio": null,
"safety_filter_level": "BLOCK_LOW_AND_ABOVE",
"person_generation": "DONT_ALLOW"
}
Schema of the request body
{
"properties": {
"guidance_type": {
"type": "string",
"enum": [
"style",
"subject"
],
"title": "Guidance Type",
"description": "Type of guidance",
"examples": [
"style",
"subject"
]
},
"ref_image_1_url": {
"type": "string",
"minLength": 1,
"format": "uri",
"title": "Ref Image 1 Url",
"description": "URL of the first reference image",
"examples": [
"https://images.pexels.com/photos/1876876/pexels-photo-1876876.jpeg"
]
},
"ref_image_1_description": {
"anyOf": [
{
"type": "string",
"maxLength": 20
},
{
"type": "null"
}
],
"title": "Ref Image 1 Description",
"description": "Description of the first reference image, if guidance_type is style, describe only the style of the reference image, if guidance_type is subject, describe only the subject of the reference image",
"examples": [
"neon vintage",
"A portrait of a caucasian young woman"
]
},
"ref_image_2_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Ref Image 2 Url",
"description": "URL of the second reference image",
"examples": [
"https://images.pexels.com/photos/5990682/pexels-photo-5990682.jpeg"
]
},
"ref_image_2_description": {
"anyOf": [
{
"type": "string",
"maxLength": 20
},
{
"type": "null"
}
],
"title": "Ref Image 2 Description",
"description": "Description of the second reference image",
"examples": [
"black and white",
"A asian man in a suit"
]
},
"subject_type": {
"anyOf": [
{
"$ref": "#/components/schemas/SubjectReferenceType"
},
{
"type": "null"
}
],
"description": "Subject type (required when guidance_type='subject')"
},
"prompt": {
"anyOf": [
{
"type": "string",
"minLength": 3
},
{
"type": "null"
}
],
"title": "Prompt",
"description": "Generation prompt. For prompting guidelines see examples [style](https://cloud.google.com/vertex-ai/generative-ai/docs/image/style-customization) , [subject](https://cloud.google.com/vertex-ai/generative-ai/docs/image/subject-customization)",
"examples": [
"generate an image of a neon sign [1] with the words: have a great day in black and white [2]"
]
},
"aspect_ratio": {
"anyOf": [
{
"type": "string",
"enum": [
"1:1",
"9:16",
"16:9",
"3:4",
"4:3"
]
},
{
"type": "null"
}
],
"title": "Aspect Ratio",
"description": "Desired aspect ratio",
"examples": [
"1:1",
"9:16",
"16:9",
"3:4",
"4:3"
]
},
"safety_filter_level": {
"$ref": "#/components/schemas/SafetyFilterLevel",
"description": "Content safety filtering level",
"default": "BLOCK_MEDIUM_AND_ABOVE"
},
"person_generation": {
"$ref": "#/components/schemas/google__genai__types__PersonGeneration",
"description": "Person generation policy",
"default": "ALLOW_ALL"
}
},
"type": "object",
"required": [
"guidance_type",
"ref_image_1_url"
],
"title": "ImagenImageGuidanceRequest",
"description": "Request model for Imagen image guidance (style/subject)."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/google-vision/image/generation/generate-variation¶
Imagen Generate Variation
Description
Apply controlled editing to an image.
Args:
- image_url: URL or path to the source image to edit.
- prompt: The prompt that describes the desired edits to the image.
- control_type (optional): Type of control to apply:
- CONTROL_TYPE_CANNY: Edge detection control
- CONTROL_TYPE_SCRIBBLE: Scribble-based control
- number_of_images (optional): Number of images to generate (1-4).
Defaults to 1.
- aspect_ratio (optional): Desired aspect ratio. Options:
- 1:1 (SQUARE): Square format
- 9:16 (PORTRAIT): Vertical portrait format
- 16:9 (LANDSCAPE): Horizontal landscape format
- 3:4 (PORTRAIT_STANDARD): Standard portrait format
- 4:3 (LANDSCAPE_STANDARD): Standard landscape format
- safety_filter_level (optional): Safety filtering level:
- BLOCK_LOW_AND_ABOVE (HIGH): Highest safety threshold
- BLOCK_MEDIUM_AND_ABOVE (MEDIUM): Medium safety threshold
- BLOCK_ONLY_HIGH (LOW): Reduced safety threshold
- person_generation (optional): Person generation control:
- ALLOW_ALL (ALL): Allow people of all ages
- ALLOW_ADULT (ADULT): Allow only adults
- DONT_ALLOW (NONE): Disable people/faces in generated images
Returns: - Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image_url": "string",
"prompt": null,
"control_type": "CONTROL_TYPE_DEFAULT",
"number_of_images": 0,
"aspect_ratio": null,
"safety_filter_level": "BLOCK_LOW_AND_ABOVE",
"person_generation": "DONT_ALLOW"
}
Schema of the request body
{
"properties": {
"image_url": {
"type": "string",
"minLength": 1,
"format": "uri",
"title": "Image Url",
"description": "URL of the source image",
"examples": [
"https://images.pexels.com/photos/18373303/pexels-photo-18373303.jpeg"
]
},
"prompt": {
"anyOf": [
{
"type": "string",
"minLength": 3
},
{
"type": "null"
}
],
"title": "Prompt",
"description": "Text prompt describing the desired changes",
"examples": [
"Add sunglasses and change the background to a beach scene"
]
},
"control_type": {
"$ref": "#/components/schemas/ControlReferenceType",
"description": "Control type for variation",
"default": "CONTROL_TYPE_CANNY",
"examples": [
"CONTROL_TYPE_CANNY",
"CONTROL_TYPE_SCRIBBLE"
]
},
"number_of_images": {
"type": "integer",
"maximum": 4.0,
"minimum": 1.0,
"title": "Number Of Images",
"description": "Number of images to generate",
"default": 1
},
"aspect_ratio": {
"anyOf": [
{
"type": "string",
"enum": [
"1:1",
"9:16",
"16:9",
"3:4",
"4:3"
]
},
{
"type": "null"
}
],
"title": "Aspect Ratio",
"description": "Desired aspect ratio",
"examples": [
"1:1",
"9:16",
"16:9",
"3:4",
"4:3"
]
},
"safety_filter_level": {
"$ref": "#/components/schemas/SafetyFilterLevel",
"description": "Content safety filtering level",
"default": "BLOCK_MEDIUM_AND_ABOVE"
},
"person_generation": {
"$ref": "#/components/schemas/google__genai__types__PersonGeneration",
"description": "Person generation policy",
"default": "ALLOW_ALL"
}
},
"type": "object",
"required": [
"image_url"
],
"title": "ImagenVariationRequest",
"description": "Request model for Imagen image variations."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/google-vision/image/generation/gemini-generate-image¶
Gemini Generate Image
Description
Generate images using Gemini 2.0 Flash with optional input images for composition.
Args:
- prompt: Text description of the desired image. To generate multiple
images, specify in the prompt (e.g., "Generate 3 images of cats").
- image_urls (optional): Array of input image URLs to use as
reference/composition elements. Supports both HTTP/HTTPS URLs and GCS URIs
(gs://).
- safety_method (optional): Safety method for the image generation.
Options:
- PROBABILITY : Use probability-based safety
- SEVERITY : Use severity-based safety
- HARM_BLOCK_METHOD_UNSPECIFIED : Use harm block method
- safety_category (optional): Safety category for the image generation.
Options:
- HARM_CATEGORY_UNSPECIFIED : Unspecified safety category
- HARM_CATEGORY_HATE_SPEECH: Hate speech category
- HARM_CATEGORY_DANGEROUS_CONTENT: Dangerous content category
- HARM_CATEGORY_HARASSMENT: Harassment category
- HARM_CATEGORY_SEXUALLY_EXPLICIT: Sexually explicit content category
- HARM_CATEGORY_CIVIC_INTEGRITY: Civic integrity category
- safety_threshold (optional): Safety threshold for the image
generation. Options:
- HARM_BLOCK_THRESHOLD_UNSPECIFIED : Unspecified safety threshold
- BLOCK_LOW_AND_ABOVE (BLOCK_LOW_AND_ABOVE): Low and above threshold
- BLOCK_MEDIUM_AND_ABOVE (BLOCK_MEDIUM_AND_ABOVE): Medium and above
threshold
- BLOCK_ONLY_HIGH (BLOCK_ONLY_HIGH): Only high threshold
- BLOCK_NONE (BLOCK_NONE): No threshold
- OFF (OFF): Off threshold
Examples:
1. Text-only generation:
2. Image composition with reference:
{
"prompt": "Combine these images into an artistic collage",
"image_urls": ["https://images.pexels.com/photos/370473/pexels-
photo-370473.jpeg", "https://images.pexels.com/photos/1687678/pexels-
photo-1687678.jpeg"]
}
Returns: - Json response with success status and the result containing generated image URLs and optional text content.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"prompt": "string",
"image_urls": null,
"safety_method": null,
"safety_category": null,
"safety_threshold": null
}
Schema of the request body
{
"properties": {
"prompt": {
"type": "string",
"minLength": 3,
"title": "Prompt",
"description": "Text description of the desired image. To generate multiple images, specify in the prompt.",
"examples": [
"A beautiful sunset over mountains",
"Combine these images into an artistic collage"
]
},
"image_urls": {
"anyOf": [
{
"items": {
"type": "string",
"minLength": 1,
"format": "uri"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Image Urls",
"description": "Optional array of input image URLs to use as reference/composition elements",
"examples": [
[
"https://images.pexels.com/photos/370473/pexels-photo-370473.jpeg",
"https://images.pexels.com/photos/1687678/pexels-photo-1687678.jpeg"
]
]
},
"safety_method": {
"anyOf": [
{
"$ref": "#/components/schemas/HarmBlockMethod"
},
{
"type": "null"
}
],
"description": "Safety filtering method",
"examples": [
"PROBABILITY",
"SEVERITY"
]
},
"safety_category": {
"anyOf": [
{
"$ref": "#/components/schemas/HarmCategory"
},
{
"type": "null"
}
],
"description": "Safety category to filter",
"examples": [
"HARM_CATEGORY_UNSPECIFIED",
"HARM_CATEGORY_HATE_SPEECH",
"HARM_CATEGORY_DANGEROUS_CONTENT",
"HARM_CATEGORY_HARASSMENT",
"HARM_CATEGORY_SEXUALLY_EXPLICIT",
"HARM_CATEGORY_CIVIC_INTEGRITY"
]
},
"safety_threshold": {
"anyOf": [
{
"$ref": "#/components/schemas/HarmBlockThreshold"
},
{
"type": "null"
}
],
"description": "Safety threshold level",
"examples": [
"BLOCK_LOW_AND_ABOVE",
"BLOCK_MEDIUM_AND_ABOVE",
"BLOCK_ONLY_HIGH",
"BLOCK_NONE"
]
}
},
"type": "object",
"required": [
"prompt"
],
"title": "GeminiGenerateImageRequest",
"description": "Request model for Gemini image generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/google-vision/image/generation/generate-image-sequence¶
Gemini Generate Image Sequence
Description
Generate interleaved text and images using Gemini 2.0 Flash.
This endpoint creates rich content that mixes text explanations with generated images, perfect for storytelling, tutorials, or step-by-step guides.
Args:
- prompt: Text prompt for interleaved content generation. Be specific
about wanting both text and images.
- safety_method (optional): Safety method for the image generation.
Options:
- PROBABILITY : Use probability-based safety
- SEVERITY : Use severity-based safety
- HARM_BLOCK_METHOD_UNSPECIFIED : Use harm block method
- safety_category (optional): Safety category for the image generation.
Options:
- HARM_CATEGORY_UNSPECIFIED : Unspecified safety category
- HARM_CATEGORY_HATE_SPEECH: Hate speech category
- HARM_CATEGORY_DANGEROUS_CONTENT: Dangerous content category
- HARM_CATEGORY_HARASSMENT: Harassment category
- HARM_CATEGORY_SEXUALLY_EXPLICIT: Sexually explicit content category
- HARM_CATEGORY_CIVIC_INTEGRITY: Civic integrity category
- safety_threshold (optional): Safety threshold for the image
generation. Options:
- HARM_BLOCK_THRESHOLD_UNSPECIFIED : Unspecified safety threshold
- BLOCK_LOW_AND_ABOVE (BLOCK_LOW_AND_ABOVE): Low and above threshold
- BLOCK_MEDIUM_AND_ABOVE (BLOCK_MEDIUM_AND_ABOVE): Medium and above
threshold
- BLOCK_ONLY_HIGH (BLOCK_ONLY_HIGH): Only high threshold
- BLOCK_NONE (BLOCK_NONE): No threshold
- OFF (OFF): Off threshold
Prompt Examples: - "Tell a short story about a magical forest with images illustrating key scenes" - "Explain how to bake a chocolate cake with step-by-step images showing the process"
Returns: - Json response with success status and the result containing both text content and generated image URLs in sequence.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"prompt": {
"type": "string",
"minLength": 3,
"title": "Prompt",
"description": "Text prompt for interleaved text and image generation",
"examples": [
"Tell a short story about a magical forest with images illustrating key scenes",
"Explain how to bake a chocolate cake with step-by-step images showing the process"
]
},
"safety_method": {
"anyOf": [
{
"$ref": "#/components/schemas/HarmBlockMethod"
},
{
"type": "null"
}
],
"description": "Safety filtering method",
"examples": [
"PROBABILITY",
"SEVERITY"
]
},
"safety_category": {
"anyOf": [
{
"$ref": "#/components/schemas/HarmCategory"
},
{
"type": "null"
}
],
"description": "Safety category to filter",
"examples": [
"HARM_CATEGORY_UNSPECIFIED",
"HARM_CATEGORY_HATE_SPEECH",
"HARM_CATEGORY_DANGEROUS_CONTENT",
"HARM_CATEGORY_HARASSMENT",
"HARM_CATEGORY_SEXUALLY_EXPLICIT",
"HARM_CATEGORY_CIVIC_INTEGRITY"
]
},
"safety_threshold": {
"anyOf": [
{
"$ref": "#/components/schemas/HarmBlockThreshold"
},
{
"type": "null"
}
],
"description": "Safety threshold level",
"examples": [
"BLOCK_LOW_AND_ABOVE",
"BLOCK_MEDIUM_AND_ABOVE",
"BLOCK_ONLY_HIGH",
"BLOCK_NONE"
]
}
},
"type": "object",
"required": [
"prompt"
],
"title": "GeminiGenerateImageSequenceRequest",
"description": "Request model for Gemini image sequence generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/openai/image/generation/generate-image¶
Gpt Generate Image
Description
Generate an image using GPT Image API.
Args:
- request: GPT image generation request containing:
- prompt: The prompt for image generation.
- number_of_images: Number of images to generate (1-10).
- aspect_ratio: The aspect ratio of the image. Options:
- "1:1" (square)
- "2:3" (landscape)
- "3:2" (portrait)
- quality: The quality of the image (medium, high, auto).
- background: Background handling (transparent, auto).
- access_token: API key for authentication.
- gpt_image_client: GPTImageAPI client instance.
Returns: Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"prompt": "string",
"number_of_images": 0,
"aspect_ratio": "1:1",
"quality": "medium",
"background": "transparent"
}
Schema of the request body
{
"properties": {
"prompt": {
"type": "string",
"minLength": 3,
"title": "Prompt",
"description": "Text description of the desired image",
"examples": [
"beautiful flowers in the garden",
"A futuristic city skyline at night"
]
},
"number_of_images": {
"type": "integer",
"maximum": 10.0,
"minimum": 1.0,
"title": "Number Of Images",
"description": "Number of images to generate",
"default": 1
},
"aspect_ratio": {
"type": "string",
"enum": [
"1:1",
"2:3",
"3:2"
],
"title": "Aspect Ratio",
"description": "Desired aspect ratio",
"default": "1:1"
},
"quality": {
"$ref": "#/components/schemas/GPTImageQuality",
"description": "Image quality setting",
"default": "auto",
"examples": [
"medium",
"high"
]
},
"background": {
"$ref": "#/components/schemas/GPTImageBackground",
"description": "Background handling",
"default": "auto",
"examples": [
"transparent",
"auto"
]
}
},
"type": "object",
"required": [
"prompt"
],
"title": "GPTGenerateImageRequest",
"description": "Request model for GPT image generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/firefly/image/generation/generate-image¶
Generate Images Async
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"x_model_version": "image3",
"prompt": "string",
"content_class": "photo",
"custom_model_id": null,
"negative_prompt": null,
"prompt_biasing_locale_code": null,
"seeds": null,
"size": {
"height": 0,
"width": 0
},
"structure": null,
"style": null,
"visual_intensity": null,
"upsampler_type": "string"
}
Schema of the request body
{
"properties": {
"x_model_version": {
"$ref": "#/components/schemas/CustomModel"
},
"prompt": {
"type": "string",
"title": "Prompt"
},
"content_class": {
"$ref": "#/components/schemas/ContentClass",
"default": "photo"
},
"custom_model_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Custom Model Id"
},
"negative_prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Negative Prompt"
},
"prompt_biasing_locale_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Prompt Biasing Locale Code"
},
"seeds": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Seeds"
},
"size": {
"$ref": "#/components/schemas/SizeImagesAsyncModel",
"default": {
"height": 2048,
"width": 2048
}
},
"structure": {
"anyOf": [
{
"$ref": "#/components/schemas/StructureModel"
},
{
"type": "null"
}
]
},
"style": {
"anyOf": [
{
"$ref": "#/components/schemas/StyleModel"
},
{
"type": "null"
}
]
},
"visual_intensity": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Visual Intensity"
},
"upsampler_type": {
"type": "string",
"title": "Upsampler Type",
"default": "default"
}
},
"type": "object",
"required": [
"x_model_version",
"prompt"
],
"title": "Body_generate_images_async_api_v1_firefly_image_generation_generate_image_post"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/firefly/image/generation/generate-variation¶
Generate Similar Images Async
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"x_model_version": "image3",
"image": {
"source": {
"upload_id": null,
"url": null
}
},
"seeds": null
}
Schema of the request body
{
"properties": {
"x_model_version": {
"$ref": "#/components/schemas/CustomModel"
},
"image": {
"$ref": "#/components/schemas/ImageReferenceModel"
},
"seeds": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Seeds"
}
},
"type": "object",
"required": [
"x_model_version",
"image"
],
"title": "Body_generate_similar_images_async_api_v1_firefly_image_generation_generate_variation_post"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/runway/image/generation/generate-image¶
Generate Image
Description
Generate an image from a text prompt or using reference images.
Args:
- request (RunwayGenerateImageRequest):
- prompt (str): Description of the desired image.
- aspect_ratio (ImageAspectRatio): Output resolution ratio.
- model ("gen4_image" | "gen4_image_turbo"): Model variant.
- reference_images_url (list[ReferenceImage] | None): Optional list of reference images with optional tags.
- seed (int | None): Seed for reproducible results.
- content_moderation (ContentModeration | None): Moderation settings.
Returns: Json response with success status and the result containing the response, including task ID, status, and result URL (if available), or any error details.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"prompt": "string",
"aspect_ratio": "1920:1080",
"model": "gen4_image",
"reference_images_url": null,
"seed": null,
"content_moderation": null
}
Schema of the request body
{
"properties": {
"prompt": {
"type": "string",
"maxLength": 1000,
"minLength": 1,
"title": "Prompt To Generate Image",
"description": "A non-empty string up to 1000 characters describing what should appear in the output.",
"examples": [
"A beautiful sea view"
]
},
"aspect_ratio": {
"$ref": "#/components/schemas/ImageAspectRatio",
"title": "Aspect ratio",
"description": "The resolution of the output image.",
"default": "1920:1080"
},
"model": {
"type": "string",
"enum": [
"gen4_image",
"gen4_image_turbo"
],
"title": "Model Variant",
"description": "The model variant to use for image generation.",
"default": "gen4_image"
},
"reference_images_url": {
"anyOf": [
{
"items": {
"$ref": "#/components/schemas/ReferenceImage"
},
"type": "array",
"maxItems": 3
},
{
"type": "null"
}
],
"title": "Reference Images",
"description": "An array of up to three images to be used as references for the generated image output.",
"examples": [
[
{
"tag": "sea",
"uri": "https://images.pexels.com/photos/31976103/pexels-photo-31976103.jpeg"
}
]
]
},
"seed": {
"anyOf": [
{
"type": "integer",
"maximum": 4294967295.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Seed",
"description": "If unspecified, a random number is chosen. Varying the seed integer is a way to get different results for the same other request parameters."
},
"content_moderation": {
"anyOf": [
{
"$ref": "#/components/schemas/ContentModeration"
},
{
"type": "null"
}
],
"description": "Settings that affect the behavior of the content moderation system."
}
},
"type": "object",
"required": [
"prompt"
],
"title": "RunwayGenerateImageRequest",
"description": "Request model for Runway text/image to image generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Image Editing¶
POST /api/v1/bria/image/editing/get-masks¶
Bria Get Masks
Description
Generate segmentation masks for an image. Creates segmentation masks that identify different objects within the image. The result url contains a zip file with k mask files in the zip.
Args:
- image_url (optional): URL of input image. Used if file not provided.
- image_file (optional): The file of the input image, in base64 format. Accepted formats are jpeg, jpg, png, webp.
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Returns: Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Image Url",
"description": "URL of reference image",
"examples": [
"https://images.pexels.com/photos/1787235/pexels-photo-1787235.jpeg"
]
},
"image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Image File",
"description": "Base64 encoded reference image"
}
},
"type": "object",
"title": "BriaGetMasksRequest"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/editing/remove-background¶
Bria Remove Background
Description
Remove background from an image using Bria's RMBG 2.0 model.
Args:
- image: The image to remove background from. Accepts URL or base64 encoded string.
- Supported formats: JPEG, JPG, PNG, WEBP.
- preserve_alpha (bool): Controls whether partially transparent areas are retained in output.
- sync (bool): If True, wait for results. If False, return status URL immediately.
- visual_input_content_moderation (bool): Enable content moderation on input visual.
- visual_output_content_moderation (bool): Enable content moderation on output visual.
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Returns: Json response with success status and the result containing the generated image URL.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image": null,
"preserve_alpha": true,
"sync": true,
"visual_input_content_moderation": true,
"visual_output_content_moderation": true
}
Schema of the request body
{
"properties": {
"image": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "string"
}
],
"title": "Image",
"description": "The image to remove background from. Accepts URL or base64 encoded string.",
"examples": [
"https://images.pexels.com/photos/1787235/pexels-photo-1787235.jpeg",
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNkYPhfDwAChwGA60e6kgAAAABJRU5ErkJggg=="
]
},
"preserve_alpha": {
"type": "boolean",
"title": "Preserve Alpha",
"description": "Controls whether partially transparent areas from input are retained in output",
"default": true
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results. If False, return status URL immediately",
"default": false
},
"visual_input_content_moderation": {
"type": "boolean",
"title": "Visual Input Content Moderation",
"description": "Enable content moderation on input visual",
"default": false
},
"visual_output_content_moderation": {
"type": "boolean",
"title": "Visual Output Content Moderation",
"description": "Enable content moderation on output visual",
"default": false
}
},
"type": "object",
"required": [
"image"
],
"title": "BriaRemoveBackgroundRequest",
"description": "Request model for BRIA Remove Background."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/editing/product-cutout¶
Bria Product Cutout
Description
Create a precise cutout of a product from any given image.
Args:
- image_url (optional): URL of input image. Used if file not provided.
- image_file (optional): The file of the input image, in base64 format. Accepted formats are jpeg, jpg, png, webp.
- force_rmbg (optional): Forces background removal, even if the original image already contains an alpha channel. Useful for refining existing foreground/background separation or ignoring unnecessary alpha channels.
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Returns: Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Image Url",
"description": "URL of reference image",
"examples": [
"https://images.pexels.com/photos/1787235/pexels-photo-1787235.jpeg"
]
},
"image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Image File",
"description": "Base64 encoded reference image"
},
"force_rmbg": {
"type": "boolean",
"title": "Force Rmbg",
"description": "Force background removal even if alpha channel exists",
"default": false
}
},
"type": "object",
"title": "BriaProductCutoutRequest"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/editing/crop-foreground¶
Bria Crop Foreground
Description
Crop the foreground from an image.
Args:
- image_url: URL of input image. Takes precedence over image_file.
- image_file: Base64 encoded input image. Used if image_url not provided.
- padding: Amount of padding around the foreground in pixels.
- force_rmbg: Force background removal even if alpha channel exists.
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Returns: Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image": null,
"padding": 0,
"force_background_detection": true,
"preserve_alpha": true,
"sync": true,
"visual_input_content_moderation": true,
"visual_output_content_moderation": true
}
Schema of the request body
{
"properties": {
"image": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "string"
}
],
"title": "Image",
"description": "The image to crop foreground from. Accepts URL or base64 encoded string.",
"examples": [
"https://images.pexels.com/photos/1787235/pexels-photo-1787235.jpeg",
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNkYPhfDwAChwGA60e6kgAAAABJRU5ErkJggg=="
]
},
"padding": {
"type": "integer",
"minimum": 0.0,
"title": "Padding",
"description": "Amount of padding around the foreground in pixels",
"default": 0
},
"force_background_detection": {
"type": "boolean",
"title": "Force Background Detection",
"description": "Force background detection and removal even if alpha channel exists",
"default": false
},
"preserve_alpha": {
"type": "boolean",
"title": "Preserve Alpha",
"description": "Controls whether alpha channel values are retained in output",
"default": true
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results. If False, return status URL immediately",
"default": false
},
"visual_input_content_moderation": {
"type": "boolean",
"title": "Visual Input Content Moderation",
"description": "Enable content moderation on input visual",
"default": false
},
"visual_output_content_moderation": {
"type": "boolean",
"title": "Visual Output Content Moderation",
"description": "Enable content moderation on output visual",
"default": false
}
},
"type": "object",
"required": [
"image"
],
"title": "BriaCropForegroundRequest",
"description": "Request model for BRIA Crop Foreground."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Image Editing Generation¶
POST /api/v1/bria/image/editing-generation/erase¶
Bria Erase
Description
Erase objects from an image using mask guidance.
Args:
- image: The image to erase objects from (URL or base64).
- mask: The mask image indicating areas to erase (URL or base64).
- mask_type: Type of mask - "manual" for user-drawn or "automatic" for algorithm-generated.
- preserve_alpha: Controls whether alpha channel values are retained in output.
- sync: If True, wait for results. If False, return status URL immediately.
- visual_input_content_moderation: Enable content moderation on input visual.
- visual_output_content_moderation: Enable content moderation on output visual.
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Returns: Json response with success status and the result containing the generated image URL.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image": null,
"mask": null,
"mask_type": "manual",
"preserve_alpha": true,
"sync": true,
"visual_input_content_moderation": true,
"visual_output_content_moderation": true
}
Schema of the request body
{
"properties": {
"image": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "string"
}
],
"title": "Image",
"description": "The image to erase objects from. Accepts URL or base64 encoded string.",
"examples": [
"https://images.pexels.com/photos/1787235/pexels-photo-1787235.jpeg",
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNkYPhfDwAChwGA60e6kgAAAABJRU5ErkJggg=="
]
},
"mask": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "string"
}
],
"title": "Mask",
"description": "The mask image indicating areas to erase. Accepts URL or base64 encoded string.",
"examples": [
"https://images.pexels.com/photos/mask.png",
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNkYPhfDwAChwGA60e6kgAAAABJRU5ErkJggg=="
]
},
"mask_type": {
"$ref": "#/components/schemas/MaskType",
"description": "Type of mask - manual for user-drawn or automatic for algorithm-generated",
"default": "manual",
"examples": [
"manual",
"automatic"
]
},
"preserve_alpha": {
"type": "boolean",
"title": "Preserve Alpha",
"description": "Controls whether alpha channel values are retained in output",
"default": true
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results. If False, return status URL immediately",
"default": false
},
"visual_input_content_moderation": {
"type": "boolean",
"title": "Visual Input Content Moderation",
"description": "Enable content moderation on input visual",
"default": false
},
"visual_output_content_moderation": {
"type": "boolean",
"title": "Visual Output Content Moderation",
"description": "Enable content moderation on output visual",
"default": false
}
},
"type": "object",
"required": [
"image",
"mask"
],
"title": "BriaEraserRequest",
"description": "Request model for BRIA Eraser."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/editing-generation/erase-foreground¶
Bria Erase Foreground
Description
Erase foreground from an image.
Args:
- image: The image to erase foreground from (URL or base64).
- preserve_alpha: Controls whether alpha channel values are retained in output.
- sync: If True, wait for results. If False, return status URL immediately.
- visual_input_content_moderation: Enable content moderation on input visual.
- visual_output_content_moderation: Enable content moderation on output visual.
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Returns: Json response with success status and the result containing the generated image URL.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image": null,
"preserve_alpha": true,
"sync": true,
"visual_input_content_moderation": true,
"visual_output_content_moderation": true
}
Schema of the request body
{
"properties": {
"image": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "string"
}
],
"title": "Image",
"description": "The image to erase foreground from. Accepts URL or base64 encoded string.",
"examples": [
"https://images.pexels.com/photos/1787235/pexels-photo-1787235.jpeg",
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNkYPhfDwAChwGA60e6kgAAAABJRU5ErkJggg=="
]
},
"preserve_alpha": {
"type": "boolean",
"title": "Preserve Alpha",
"description": "Controls whether alpha channel values are retained in output",
"default": true
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results. If False, return status URL immediately",
"default": false
},
"visual_input_content_moderation": {
"type": "boolean",
"title": "Visual Input Content Moderation",
"description": "Enable content moderation on input visual",
"default": false
},
"visual_output_content_moderation": {
"type": "boolean",
"title": "Visual Output Content Moderation",
"description": "Enable content moderation on output visual",
"default": false
}
},
"type": "object",
"required": [
"image"
],
"title": "BriaEraseForegroundRequest",
"description": "Request model for BRIA Erase Foreground."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/editing-generation/inpaint¶
Bria Inpainting
Description
Generate objects by prompt in a specific masked region (gen_fill). Supports custom border_only mask generation for backward compatibility.
Args:
- image: The image to apply generative fill to. Accepts URL or base64 encoded string.
- Supported formats: JPEG, JPG, PNG, WEBP.
- mask: The mask image indicating areas to fill. Accepts URL or base64 encoded string. Optional when mask_type is 'border_only'.
- prompt: Text description for object generation in masked region.
- mask_type: Type of mask - manual, automatic, or border_only for custom border processing.
- sync: If True, wait for results. If False, return status URL immediately.
- negative_prompt (optional): Text description of elements to avoid.
- seed (optional): Seed for reproducible results.
- preserve_alpha: Controls whether alpha channel values are retained in output.
- prompt_content_moderation: Enable content moderation on prompts.
- visual_input_content_moderation: Enable content moderation on input visual.
- visual_output_content_moderation: Enable content moderation on output visual.
- border_percentage (optional): Percentage of the border to inpaint when using border_only mode.
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Returns: Json response with success status and the result containing the generated image URL.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image": null,
"mask": null,
"prompt": "string",
"mask_type": "manual",
"sync": true,
"negative_prompt": null,
"seed": null,
"preserve_alpha": true,
"prompt_content_moderation": true,
"visual_input_content_moderation": true,
"visual_output_content_moderation": true,
"border_percentage": null
}
Schema of the request body
{
"properties": {
"image": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "string"
}
],
"title": "Image",
"description": "The image to apply generative fill to. Accepts URL or base64 encoded string.",
"examples": [
"https://images.pexels.com/photos/1787235/pexels-photo-1787235.jpeg",
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNkYPhfDwAChwGA60e6kgAAAABJRU5ErkJggg=="
]
},
"mask": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Mask",
"description": "The mask image indicating areas to fill. Accepts URL or base64 encoded string. Optional when mask_type is 'border_only'."
},
"prompt": {
"type": "string",
"minLength": 4,
"title": "Prompt",
"description": "Text description for the object generation.",
"examples": [
"A camera on the beach"
]
},
"mask_type": {
"$ref": "#/components/schemas/MaskType",
"description": "Type of mask - manual, automatic, or border_only for custom border processing",
"default": "manual",
"examples": [
"manual",
"automatic",
"border_only"
]
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results. If False, return status URL immediately",
"default": false
},
"negative_prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Negative Prompt",
"description": "Elements to exclude from generation",
"examples": [
"text",
"logo",
"watermark",
"background"
]
},
"seed": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Seed",
"description": "Seed for reproducible results"
},
"preserve_alpha": {
"type": "boolean",
"title": "Preserve Alpha",
"description": "Controls whether alpha channel values are retained in output",
"default": true
},
"prompt_content_moderation": {
"type": "boolean",
"title": "Prompt Content Moderation",
"description": "Enable content moderation on prompts",
"default": true
},
"visual_input_content_moderation": {
"type": "boolean",
"title": "Visual Input Content Moderation",
"description": "Enable content moderation on input visual",
"default": false
},
"visual_output_content_moderation": {
"type": "boolean",
"title": "Visual Output Content Moderation",
"description": "Enable content moderation on output visual",
"default": false
},
"border_percentage": {
"anyOf": [
{
"type": "number",
"maximum": 0.3,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Border Percentage",
"description": "Percentage of border to inpaint when using border_only mode"
}
},
"type": "object",
"required": [
"image",
"prompt"
],
"title": "BriaInpaintingRequest",
"description": "Request model for BRIA Generative Fill (gen_fill)."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/editing-generation/expand-image¶
Bria Expand Image
Description
Expand an image to a specified canvas size with flexible positioning options.
This method supports two modes: 1. Canvas Size Mode: Provide canvas_size with position or padding percentages 2. Aspect Ratio Mode: Provide aspect_ratio with position or padding percentages
Args: - image (required): Input image (URL or base64).
Canvas/Aspect Ratio Parameters: - canvas_size (optional): Target canvas size as tuple (width, height). If provided, overrides aspect_ratio. - aspect_ratio (optional): Target aspect ratio for automatic canvas sizing.
Positioning Parameters (choose one): - position (optional): Predefined positioning ("upper_left", "upper_right", "bottom_left", "bottom_right", "right_center", "left_center", "upper_center", "bottom_center", "center_vertical", "center_horizontal"). - padding_left (optional): Percentage of left padding (0.0-1.0). - padding_right (optional): Percentage of right padding (0.0-1.0). - padding_top (optional): Percentage of top padding (0.0-1.0). - padding_bottom (optional): Percentage of bottom padding (0.0-1.0).
Generation Parameters: - prompt (optional): Text description for expanded area generation. - seed (optional): Seed for reproducible results. - negative_prompt (optional): Elements to exclude from generation.
V2 API Parameters: - preserve_alpha (bool, default=True): Preserve alpha channel in the output. - visual_input_content_moderation (bool, default=False): Content moderation for input visuals. - visual_output_content_moderation (bool, default=False): Content moderation for output visuals. - prompt_content_moderation (bool, default=False): Content moderation for prompts. - sync (bool, default=False): If True, wait for results.
Examples:
1. Canvas Size with Predefined Position:
{
"image":
"https://upload.wikimedia.org/wikipedia/commons/thumb/8/80/Wikipedia-
logo-v2.svg/1920px-Wikipedia-logo-v2.svg.png",
"canvas_size": [1024, 1024],
"position": "center_vertical",
"prompt": "beautiful sunset background",
"sync": true,
"preserve_alpha": true,
"visual_input_content_moderation": false,
"visual_output_content_moderation": false,
"prompt_content_moderation": false
}
2. Aspect Ratio with Predefined Position:
{
"image":
"https://upload.wikimedia.org/wikipedia/commons/thumb/8/80/Wikipedia-
logo-v2.svg/1920px-Wikipedia-logo-v2.svg.png",
"aspect_ratio": "4:3",
"position": "upper_center",
"prompt": "sky and clouds above",
"negative_prompt": "buildings, urban elements",
"sync": true,
"preserve_alpha": true,
"visual_input_content_moderation": false,
"visual_output_content_moderation": false,
"prompt_content_moderation": false
}
3. Aspect Ratio with Custom Padding:
{
"image":
"https://upload.wikimedia.org/wikipedia/commons/thumb/8/80/Wikipedia-
logo-v2.svg/1920px-Wikipedia-logo-v2.svg.png",
"aspect_ratio": "9:16",
"padding_left": 0.1,
"padding_right": 0.1,
"padding_top": 0.2,
"padding_bottom": 0.05,
"prompt": "green mountain landscape background",
"sync": true,
"preserve_alpha": true,
"visual_input_content_moderation": false,
"visual_output_content_moderation": false,
"prompt_content_moderation": false
}
4. Canvas Size with Custom Padding:
{
"image":
"https://upload.wikimedia.org/wikipedia/commons/thumb/8/80/Wikipedia-
logo-v2.svg/1920px-Wikipedia-logo-v2.svg.png",
"canvas_size": [1600, 900],
"padding_left": 0.15,
"padding_right": 0.15,
"padding_top": 0.4,
"padding_bottom": 0.1,
"prompt": "forest environment",
"sync": true,
"preserve_alpha": true,
"visual_input_content_moderation": false,
"visual_output_content_moderation": false,
"prompt_content_moderation": false
}
Returns: Json response with success status and the result containing the expanded image URL.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image": null,
"canvas_size": null,
"aspect_ratio": null,
"position": null,
"padding_left": null,
"padding_right": null,
"padding_top": null,
"padding_bottom": null,
"prompt": null,
"seed": null,
"negative_prompt": null,
"preserve_alpha": true,
"visual_input_content_moderation": true,
"visual_output_content_moderation": true,
"prompt_content_moderation": true,
"sync": true
}
Schema of the request body
{
"properties": {
"image": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "string"
}
],
"title": "Image",
"description": "Input image (URL or base64)",
"examples": [
"https://images.pexels.com/photos/31976103/pexels-photo-31976103.jpeg"
]
},
"canvas_size": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Canvas Size",
"description": "Canvas size (width, height)",
"examples": [
[
2048,
2048
],
[
3072,
2048
]
]
},
"aspect_ratio": {
"anyOf": [
{
"type": "string",
"enum": [
"1:1",
"2:3",
"3:2",
"3:4",
"4:3",
"16:9",
"9:16",
"4:5",
"5:4"
]
},
{
"type": "null"
}
],
"title": "Aspect Ratio",
"description": "Target aspect ratio for automatic mode"
},
"position": {
"anyOf": [
{
"$ref": "#/components/schemas/ManualPlacement"
},
{
"type": "null"
}
],
"description": "Image positioning for automatic mode",
"examples": [
"center_horizontal",
"center_vertical"
]
},
"padding_left": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Padding Left",
"description": "Percentage of left padding to add"
},
"padding_right": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Padding Right",
"description": "Percentage of right padding to add"
},
"padding_top": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Padding Top",
"description": "Percentage of top padding to add"
},
"padding_bottom": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Padding Bottom",
"description": "Percentage of bottom padding to add"
},
"prompt": {
"anyOf": [
{
"type": "string",
"minLength": 4
},
{
"type": "null"
}
],
"title": "Prompt",
"description": "Text description for expanded area generation",
"default": "",
"examples": [
"A mountain landscape with a lake",
"A cozy coffee shop interior",
"Professional headshot of a business person"
]
},
"seed": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Seed",
"description": "Seed for reproducible results"
},
"negative_prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Negative Prompt",
"description": "Elements to exclude",
"examples": [
"text",
"logo",
"watermark",
"background"
]
},
"preserve_alpha": {
"type": "boolean",
"title": "Preserve Alpha",
"description": "Preserve alpha channel in the output",
"default": true
},
"visual_input_content_moderation": {
"type": "boolean",
"title": "Visual Input Content Moderation",
"description": "Content moderation for input visuals",
"default": false
},
"visual_output_content_moderation": {
"type": "boolean",
"title": "Visual Output Content Moderation",
"description": "Content moderation for output visuals",
"default": false
},
"prompt_content_moderation": {
"type": "boolean",
"title": "Prompt Content Moderation",
"description": "Content moderation for prompts",
"default": false
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results",
"default": false
}
},
"type": "object",
"required": [
"image"
],
"title": "BriaExpandImageRequest"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/editing-generation/blur-background¶
Bria Blur Background
Description
Blur the background of an image . Automatically detects and blurs the background while keeping the foreground subjects in focus.
Args:
- image: The image to blur background from. Accepts URL or base64 encoded string.
- Supported formats: JPEG, JPG, PNG, WEBP.
- scale: Scale for determining how blurry the background should be (1-5).
- preserve_alpha: Controls whether alpha channel values are retained in output.
- sync: If True, wait for results. If False, return status URL immediately.
- visual_input_content_moderation: Enable content moderation on input visual.
- visual_output_content_moderation: Enable content moderation on output visual.
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Returns: Json response with success status and the result containing the generated image URL.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image": null,
"scale": 0,
"preserve_alpha": true,
"sync": true,
"visual_input_content_moderation": true,
"visual_output_content_moderation": true
}
Schema of the request body
{
"properties": {
"image": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "string"
}
],
"title": "Image",
"description": "The image to blur background from. Accepts URL or base64 encoded string.",
"examples": [
"https://images.pexels.com/photos/1787235/pexels-photo-1787235.jpeg",
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNkYPhfDwAChwGA60e6kgAAAABJRU5ErkJggg=="
]
},
"scale": {
"type": "integer",
"maximum": 5.0,
"minimum": 1.0,
"title": "Scale",
"description": "Scale for determining how blurry the background should be (1-5)",
"default": 5
},
"preserve_alpha": {
"type": "boolean",
"title": "Preserve Alpha",
"description": "Controls whether alpha channel values are retained in output",
"default": true
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results. If False, return status URL immediately",
"default": false
},
"visual_input_content_moderation": {
"type": "boolean",
"title": "Visual Input Content Moderation",
"description": "Enable content moderation on input visual",
"default": false
},
"visual_output_content_moderation": {
"type": "boolean",
"title": "Visual Output Content Moderation",
"description": "Enable content moderation on output visual",
"default": false
}
},
"type": "object",
"required": [
"image"
],
"title": "BriaBlurBackgroundRequest",
"description": "Request model for BRIA Blur Background."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/editing-generation/generate-solid-background¶
Bria Generate Solid Background
Description
Creates a professional packshot of a product with consistent size and positioning. The output is a 2000x2000 px image, with the product size and location according to best practices.
Args:
- image_url (optional): URL of product image. Max 12MB. Formats: jpeg, jpg, png, webp.
- image_file (optional): Base64 encoded product image. Max 12MB. Formats: jpeg, jpg, png, webp.
- background_color (optional): Hex color code for background. Use 'transparent' for transparent background.
- force_rmbg: Forces background removal even if the original image already contains an alpha channel. Useful for refining existing foreground/background separation.
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Returns: Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Image Url",
"description": "URL of reference image",
"examples": [
"https://images.pexels.com/photos/1787235/pexels-photo-1787235.jpeg"
]
},
"image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Image File",
"description": "Base64 encoded reference image"
},
"background_color": {
"type": "string",
"title": "Background Color",
"description": "Hex color code for background or 'transparent'",
"default": "#FFFFFF"
},
"force_rmbg": {
"type": "boolean",
"title": "Force Rmbg",
"description": "Force background removal even if alpha channel exists",
"default": false
}
},
"type": "object",
"title": "BriaGenerateSolidBackgroundRequest"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/editing-generation/generate-background¶
Bria Generate Background
Description
Replace image background (replace_background). Places foreground subjects on new backgrounds generated based on a reference image or text prompt.
Args:
- image: The image to replace background for. Accepts URL or base64 encoded string.
- Supported formats: JPEG, JPG, PNG, WEBP.
- ref_images (optional): Reference image(s) for background generation. Accepts URL or base64 encoded string.
- enhance_ref_images: Process reference image for optimal results.
- prompt (optional): Text description of desired background. Either ref_images or prompt required.
- refine_prompt: Use LLM to optimize prompt for better results.
- prompt_content_moderation: Enable content moderation on prompts.
- negative_prompt (optional): Elements to exclude from generation (only when fast=false).
- original_quality: Maintain original image size, otherwise scale to 1MP.
- force_background_detection: Force background detection even if alpha channel exists.
- sync: If True, wait for results. If False, return status URL immediately.
- fast: Use fast generation mode for speed/quality balance.
- visual_input_content_moderation: Enable content moderation on input visual.
- visual_output_content_moderation: Enable content moderation on output visual.
- seed (optional): Seed for reproducible results.
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Returns: Json response with success status and the result containing the generated image URL.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image": null,
"ref_images": null,
"enhance_ref_images": true,
"prompt": null,
"refine_prompt": true,
"prompt_content_moderation": true,
"negative_prompt": null,
"original_quality": true,
"force_background_detection": true,
"sync": true,
"fast": true,
"visual_input_content_moderation": true,
"visual_output_content_moderation": true,
"seed": null
}
Schema of the request body
{
"properties": {
"image": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "string"
}
],
"title": "Image",
"description": "The image to replace background for. Accepts URL or base64 encoded string.",
"examples": [
"https://images.pexels.com/photos/1787235/pexels-photo-1787235.jpeg",
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNkYPhfDwAChwGA60e6kgAAAABJRU5ErkJggg=="
]
},
"ref_images": {
"anyOf": [
{
"items": {
"type": "string",
"minLength": 1,
"format": "uri"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Ref Images",
"description": "Reference image(s) for background generation. Accepts single image (URL or base64) or list of images.",
"examples": [
[
"https://images.pexels.com/photos/31976103/pexels-photo-31976103.jpeg",
"https://images.pexels.com/photos/32480719/pexels-photo-32480719.jpeg"
],
[
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNkYPhfDwAChwGA60e6kgAAAABJRU5ErkJggg=="
]
]
},
"enhance_ref_images": {
"type": "boolean",
"title": "Enhance Ref Images",
"description": "Process reference image for optimal results",
"default": true
},
"prompt": {
"anyOf": [
{
"type": "string",
"minLength": 4
},
{
"type": "null"
}
],
"title": "Prompt",
"description": "Text description of desired background. Either ref_images or prompt required.",
"examples": [
"A mountain landscape with a lake",
"A cozy coffee shop interior"
]
},
"refine_prompt": {
"type": "boolean",
"title": "Refine Prompt",
"description": "Use LLM to optimize prompt for better results",
"default": true
},
"prompt_content_moderation": {
"type": "boolean",
"title": "Prompt Content Moderation",
"description": "Enable content moderation on prompts",
"default": true
},
"negative_prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Negative Prompt",
"description": "Elements to exclude from generation (only when fast=false)",
"examples": [
"text",
"logo",
"watermark",
"background"
]
},
"original_quality": {
"type": "boolean",
"title": "Original Quality",
"description": "Maintain original image size, otherwise scale to 1MP",
"default": false
},
"force_background_detection": {
"type": "boolean",
"title": "Force Background Detection",
"description": "Force background detection even if alpha channel exists",
"default": false
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results. If False, return status URL immediately",
"default": false
},
"fast": {
"type": "boolean",
"title": "Fast",
"description": "Use fast generation mode for speed/quality balance",
"default": false
},
"visual_input_content_moderation": {
"type": "boolean",
"title": "Visual Input Content Moderation",
"description": "Enable content moderation on input visual",
"default": false
},
"visual_output_content_moderation": {
"type": "boolean",
"title": "Visual Output Content Moderation",
"description": "Enable content moderation on output visual",
"default": false
},
"seed": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Seed",
"description": "Seed for reproducible results"
}
},
"type": "object",
"required": [
"image"
],
"title": "BriaGenerateBackgroundRequest",
"description": "Request model for BRIA Generate Background (replace_background)."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/editing-generation/generate-product-shadow¶
Bria Generate Product Shadow
Description
Creates a shadow effect for a product image with a transparent background. Note: Input image must have transparent background. Use product cutout endpoint first if needed.
Args:
- shadow_type (optional): Type of shadow.
- shadow_color (optional): Hex color code for shadow.
- shadow_intensity (optional): Shadow intensity from 0-100.
- shadow_offset (optional): [x,y] position of shadow relative to object in pixels.
- shadow_blur (optional): Controls the blur level of the shadow's edges. Default for 'shadow_type'=regular is 15, while for 'shadow_type'=float is 20.
- shadow_width (optional): Width of elliptical shadow in pixels for floating shadows. Could be positive or negative.
- shadow_height: (optional): Height of elliptical shadow in pixels. Default is 70.
- background_color (optional): Hex color code for background. Omit for transparent background.
- force_rmbg: Forces background removal even if the original image already contains an alpha channel. Useful for refining existing foreground/background separation.
- image_url (optional): URL of product image/cutout. Takes precedence over image_file. Max 12MB. Formats: jpeg, jpg, png, webp.
- image_file (optional): Base64 encoded product image/cutout. Used if image_url not provided. Max 12MB. Formats: jpeg, jpg, png, webp.
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image_url": null,
"image_file": null,
"shadow_type": null,
"shadow_color": null,
"shadow_intensity": null,
"shadow_offset": null,
"shadow_blur": null,
"shadow_width": null,
"shadow_height": null,
"background_color": null,
"force_rmbg": true
}
Schema of the request body
{
"properties": {
"image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Image Url",
"description": "URL of input image",
"examples": [
"https://images.pexels.com/photos/31976103/pexels-photo-31976103.jpeg"
]
},
"image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Image File",
"description": "Base64 encoded input image"
},
"shadow_type": {
"anyOf": [
{
"type": "string",
"enum": [
"regular",
"float"
]
},
{
"type": "null"
}
],
"title": "Shadow Type",
"description": "Type of shadow",
"default": "regular"
},
"shadow_color": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Shadow Color",
"description": "Hex color code for shadow",
"default": "#000000"
},
"shadow_intensity": {
"anyOf": [
{
"type": "integer",
"maximum": 100.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Shadow Intensity",
"description": "Shadow intensity",
"default": 60
},
"shadow_offset": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Shadow Offset",
"description": "Shadow position relative to object in pixels (x, y)",
"default": [
0,
15
]
},
"shadow_blur": {
"anyOf": [
{
"type": "integer",
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Shadow Blur",
"description": "Blur level of shadow edges",
"examples": [
10,
20,
30
]
},
"shadow_width": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Shadow Width",
"description": "Width of elliptical shadow in pixels",
"examples": [
100,
200,
300
]
},
"shadow_height": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Shadow Height",
"description": "Height of elliptical shadow in pixels",
"examples": [
100,
200,
300
]
},
"background_color": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Background Color",
"description": "Hex color code for background",
"examples": [
"#FF0000",
"#00FF00",
"#0000FF"
]
},
"force_rmbg": {
"type": "boolean",
"title": "Force Rmbg",
"description": "Force background removal even if alpha channel exists",
"default": false
}
},
"type": "object",
"title": "BriaGenerateProductShadowRequest"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/editing-generation/generate-product-background-by-text¶
Bria Generate Product Background By Text
Description
Creates enriched product shots by placing them in various environments using textual descriptions. Additionally, you can change the image size of the final result as well as the positioning of the product in the image. Uses BRIA 2.3 ControlNet BG-Gen.
Args:
- scene_description: Text description of desired scene/background (English only).
- image_url (optional): URL of product shot to place in lifestyle scene. Max 12MB JPEG/PNG/WEBP.
- image_file (optional): Base64 encoded product shot if no image_url. Max 12MB JPEG/PNG/WEBP.
- sync: When True, responses are synchronous. Default False for asynchronous responses with immediate URLs.
- fast: When True, uses fast generation mode balancing speed and quality.
- optimize_description: When True, optimizes scene description using Meta Llama 3.
- num_results: Number of lifestyle shots to generate. Maximum value is 4.
- placement_type: Controls product positioning. Options are 'original', 'automatic', 'manual_placement', 'manual_padding', 'custom_coordinates', 'automatic_aspect_ratio'.
- original_quality: For placement_type="original", preserves input image size.
- shot_size: Desired output dimensions [width, height]. For optimal results, the total number of pixels should be around 1,000,000.
- manual_placement_selection: Placement positions for manual_placement.
- padding_values: Padding [left,right,top,bottom] for manual_padding.
- force_rmbg: Forces background removal even if the original image already contains an alpha channel. Useful for refining existing foreground/background separation.
- exclude_elements (optional): Elements to exclude from scene. English only, requires fast=False.
- foreground_image_size (optional): Desired foreground image dimensions [width, height].
- foreground_image_location (optional): Desired foreground image position [x,y].
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Returns: Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"scene_description": "string",
"aspect_ratio": "1:1",
"num_results": 0,
"image_url": null,
"image_file": null,
"fast": true,
"sync": true,
"optimize_description": true,
"original_quality": true,
"force_rmbg": true,
"placement_type": "original",
"manual_placement_selection": "upper_left",
"padding_values": [],
"exclude_elements": null,
"canvas_for_packshot_size": null,
"foreground_image_size": null,
"foreground_image_location": null
}
Schema of the request body
{
"properties": {
"scene_description": {
"type": "string",
"minLength": 4,
"title": "Scene Description",
"description": "Text description of desired scene/background (English only).",
"examples": [
"A mountain landscape with a lake",
"A cozy coffee shop interior"
]
},
"aspect_ratio": {
"type": "string",
"enum": [
"1:1",
"2:3",
"3:2",
"3:4",
"4:3",
"16:9",
"9:16",
"4:5",
"5:4"
],
"title": "Aspect Ratio",
"description": "Image aspect ratio",
"default": "1:1"
},
"num_results": {
"type": "integer",
"maximum": 4.0,
"minimum": 1.0,
"title": "Num Results",
"description": "Number of images to generate",
"default": 1
},
"image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Image Url",
"description": "URL of reference image",
"examples": [
"https://images.pexels.com/photos/31976103/pexels-photo-31976103.jpeg"
]
},
"image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Image File",
"description": "Base64 encoded reference image"
},
"fast": {
"type": "boolean",
"title": "Fast",
"description": "Use fast generation mode",
"default": true
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results",
"default": true
},
"optimize_description": {
"type": "boolean",
"title": "Optimize Description",
"description": "Optimize scene description using Meta Llama 3",
"default": false
},
"original_quality": {
"type": "boolean",
"title": "Original Quality",
"description": "Preserve input image size for 'original' placement",
"default": false
},
"force_rmbg": {
"type": "boolean",
"title": "Force Rmbg",
"description": "Force background removal even if alpha channel exists",
"default": false
},
"placement_type": {
"$ref": "#/components/schemas/PlacementType",
"description": "Controls product positioning.",
"default": "original",
"examples": [
"original",
"automatic"
]
},
"manual_placement_selection": {
"$ref": "#/components/schemas/ManualPlacement",
"description": "Placement position for manual_placement",
"default": "center_horizontal",
"examples": [
"upper_left",
"bottom_left"
]
},
"padding_values": {
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
},
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array",
"maxItems": 4,
"minItems": 4,
"title": "Padding Values",
"description": "Padding [left,right,top,bottom] for manual_padding",
"default": [
0,
0,
0,
0
]
},
"exclude_elements": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Exclude Elements",
"description": "Elements to exclude from scene (English only)",
"examples": [
"text",
"logo",
"watermark",
"background"
]
},
"canvas_for_packshot_size": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Canvas For Packshot Size",
"description": "Desired canvas for packshot size",
"examples": [
[
2048,
2048
],
[
3072,
2048
]
]
},
"foreground_image_size": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Foreground Image Size",
"description": "Desired foreground image dimensions [width, height]",
"examples": [
[
2048,
2048
],
[
3072,
2048
]
]
},
"foreground_image_location": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Foreground Image Location",
"description": "Desired foreground image position [x,y]",
"examples": [
[
100,
100
],
[
200,
200
]
]
}
},
"type": "object",
"required": [
"scene_description"
],
"title": "BriaGenerateProductBackgroundByTextRequest"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/editing-generation/generate-product-background-by-image¶
Bria Generate Product Background By Image
Description
Creates enriched product shots by placing them in various environments using reference images. Additionally, you can change the image size of the final result as well as the positioning of the product in the image. Uses BRIA 2.3 ControlNet BG-Gen.
Args:
- image_url (optional): URL of product shot to place in lifestyle scene. Max 12MB JPEG/PNG/WEBP.
- image_file (optional): Base64 encoded product shot if no image_url. Max 12MB JPEG/PNG/WEBP.
- ref_image_urls (optional): URLs of reference images to generate from.
- ref_image_file (optional): Base64 encoded reference images if no ref_image_urls.
- sync: When True, responses are synchronous.
- enhance_ref_image: Process reference image for optimal results.
- ref_image_influence: Weight of reference image in generation.
- num_results: Number of lifestyle shots to generate. Maximum value is 4.
- placement_type: Controls product positioning. Options are 'original', 'automatic', 'manual_placement', 'manual_padding', 'custom_coordinates', 'automatic_aspect_ratio'.
- original_quality: For placement_type="original", preserves input image size.
- shot_size: Desired output dimensions.
- manual_placement_selection: Placement positions for manual_placement.
- padding_values: Padding for manual_padding.
- force_rmbg: Forces background removal even if the original image already has an alpha channel.
- foreground_image_size (optional): Desired foreground image dimensions.
- foreground_image_location (optional): Desired foreground image position.
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Returns: Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"aspect_ratio": "1:1",
"num_results": 0,
"image_url": null,
"image_file": null,
"ref_image_urls": null,
"ref_image_file": null,
"sync": true,
"enhance_ref_image": true,
"ref_image_influence": 10.12,
"original_quality": true,
"force_rmbg": true,
"placement_type": "original",
"manual_placement_selection": "upper_left",
"padding_values": [],
"canvas_for_packshot_size": null,
"foreground_image_size": null,
"foreground_image_location": null
}
Schema of the request body
{
"properties": {
"aspect_ratio": {
"type": "string",
"enum": [
"1:1",
"2:3",
"3:2",
"3:4",
"4:3",
"16:9",
"9:16",
"4:5",
"5:4"
],
"title": "Aspect Ratio",
"description": "Image aspect ratio",
"default": "1:1"
},
"num_results": {
"type": "integer",
"maximum": 4.0,
"minimum": 1.0,
"title": "Num Results",
"description": "Number of images to generate",
"default": 1
},
"image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Image Url",
"description": "URL of reference image",
"examples": [
"https://images.pexels.com/photos/31976103/pexels-photo-31976103.jpeg"
]
},
"image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Image File",
"description": "Base64 encoded reference image"
},
"ref_image_urls": {
"anyOf": [
{
"items": {
"type": "string",
"minLength": 1,
"format": "uri"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Ref Image Urls",
"description": "URLs of reference images to generate from",
"examples": [
[
"https://images.pexels.com/photos/31976103/pexels-photo-31976103.jpeg"
],
[
"https://images.pexels.com/photos/33344545/pexels-photo-33344545.jpeg"
]
]
},
"ref_image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Ref Image File",
"description": "Base64 encoded reference images"
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results",
"default": true
},
"enhance_ref_image": {
"type": "boolean",
"title": "Enhance Ref Image",
"description": "Process reference image for optimal results",
"default": true
},
"ref_image_influence": {
"type": "number",
"maximum": 2.0,
"minimum": 0.0,
"title": "Ref Image Influence",
"description": "Weight of reference image in generation",
"default": 1.0
},
"original_quality": {
"type": "boolean",
"title": "Original Quality",
"description": "Preserve input image size for 'original' placement",
"default": false
},
"force_rmbg": {
"type": "boolean",
"title": "Force Rmbg",
"description": "Force background removal even if alpha channel exists",
"default": false
},
"placement_type": {
"$ref": "#/components/schemas/PlacementType",
"description": "Controls product positioning.",
"default": "original",
"examples": [
"original",
"automatic"
]
},
"manual_placement_selection": {
"$ref": "#/components/schemas/ManualPlacement",
"description": "Placement position for manual_placement",
"default": "center_horizontal",
"examples": [
"upper_left",
"bottom_left"
]
},
"padding_values": {
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
},
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array",
"maxItems": 4,
"minItems": 4,
"title": "Padding Values",
"description": "Padding [left,right,top,bottom] for manual_padding",
"default": [
0,
0,
0,
0
]
},
"canvas_for_packshot_size": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Canvas For Packshot Size",
"description": "Desired canvas for packshot size",
"examples": [
[
2048,
2048
],
[
3072,
2048
]
]
},
"foreground_image_size": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Foreground Image Size",
"description": "Desired foreground image dimensions [width, height]",
"examples": [
[
2048,
2048
],
[
3072,
2048
]
]
},
"foreground_image_location": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Foreground Image Location",
"description": "Desired foreground image position [x,y]",
"examples": [
[
100,
100
],
[
200,
200
]
]
}
},
"type": "object",
"title": "BriaGenerateProductBackgroundByImageRequest"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/editing-generation/enhance-image¶
Bria Enhance Image
Description
Enhance an image by improving visual quality, generating richer details, and sharper textures.
This endpoint supports upscaling to higher resolutions while enhancing image quality. Unlike the upscale endpoint, this regenerates the image to enhance visual richness.
Args: - image (required): Input image (URL or base64). Supported formats: JPEG, JPG, PNG, WEBP.
Enhancement Parameters: - steps_num (int, 10-50, default=20): Number of enhancement steps. Higher values improve quality but increase processing time. - resolution (str, default="1MP"): Target output resolution. Options: "1MP", "2MP", "4MP". - seed (int, optional): Seed for reproducible results.
Content Moderation: - visual_input_content_moderation (bool, default=False): Scan input image for inappropriate content. - visual_output_content_moderation (bool, default=False): Evaluate enhanced image output for safety.
Processing Options: - sync (bool, default=False): If True, wait for results. If False, return status URL immediately. - preserve_alpha (bool, default=True): Preserve alpha channel in output if present in input.
Returns: Json response with success status and the result containing the enhanced image URL.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image": null,
"sync": true,
"visual_input_content_moderation": true,
"visual_output_content_moderation": true,
"seed": null,
"steps_num": null,
"resolution": "1MP",
"preserve_alpha": true
}
Schema of the request body
{
"properties": {
"image": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "string"
}
],
"title": "Image",
"description": "Input image (URL or base64)",
"examples": [
"https://images.pexels.com/photos/31976103/pexels-photo-31976103.jpeg"
]
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results",
"default": false
},
"visual_input_content_moderation": {
"type": "boolean",
"title": "Visual Input Content Moderation",
"description": "Content moderation for input visuals",
"default": false
},
"visual_output_content_moderation": {
"type": "boolean",
"title": "Visual Output Content Moderation",
"description": "Content moderation for output visuals",
"default": false
},
"seed": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Seed",
"description": "Seed for reproducible results"
},
"steps_num": {
"anyOf": [
{
"type": "integer",
"maximum": 50.0,
"minimum": 10.0
},
{
"type": "null"
}
],
"title": "Steps Num",
"description": "Number of enhancement steps. Higher values improve quality but increase processing time.",
"default": 20
},
"resolution": {
"$ref": "#/components/schemas/EnhanceResolution",
"description": "Target output resolution of the enhanced image",
"default": "1MP"
},
"preserve_alpha": {
"type": "boolean",
"title": "Preserve Alpha",
"description": "Preserve alpha channel in the output",
"default": true
}
},
"type": "object",
"required": [
"image"
],
"title": "BriaEnhanceImageRequest",
"description": "Request model for BRIA Enhance Image."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria/image/editing-generation/upscale-image¶
Bria Upscale Image
Description
Increases the resolution of an image by a factor of 2 or 4. The input image should be less than 2 megapixels. Maximum output resolution: 8192x8192 pixels.
Args:
- image: The image to upscale. Accepts URL or base64 encoded string.
- Supported formats: JPEG, JPG, PNG, WEBP.
- preserve_alpha (bool): Controls whether alpha channel values are retained in output. When true, maintains original transparency. When false, output is fully opaque.
- Default: true.
- desired_increase (int): Factor by which to increase resolution (2 or 4). Default: 2.
- sync (bool): If True, wait for results. If False, return status URL immediately.
- Note: sync=true requires input ≤ 2 megapixels. Default: false.
- visual_input_content_moderation (bool): Enable content moderation on input visual. Default: false.
- visual_output_content_moderation (bool): Enable content moderation on output visual. Default: false.
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Returns: Json response with success status and the result containing the generated image URL.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image": null,
"preserve_alpha": true,
"desired_increase": 0,
"sync": true,
"visual_input_content_moderation": true,
"visual_output_content_moderation": true
}
Schema of the request body
{
"properties": {
"image": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "string"
}
],
"title": "Image",
"description": "The image to upscale. Accepts URL or base64 encoded string.",
"examples": [
"https://images.pexels.com/photos/733835/pexels-photo-733835.jpeg",
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNkYPhfDwAChwGA60e6kgAAAABJRU5ErkJggg=="
]
},
"preserve_alpha": {
"type": "boolean",
"title": "Preserve Alpha",
"description": "Controls whether the alpha channel values from input are retained in output",
"default": true
},
"desired_increase": {
"type": "integer",
"enum": [
2,
4
],
"title": "Desired Increase",
"description": "Factor by which to increase resolution (2 or 4)",
"default": 2
},
"sync": {
"type": "boolean",
"title": "Sync",
"description": "If True, wait for results. If False, return status URL immediately",
"default": false
},
"visual_input_content_moderation": {
"type": "boolean",
"title": "Visual Input Content Moderation",
"description": "Enable content moderation on input visual",
"default": false
},
"visual_output_content_moderation": {
"type": "boolean",
"title": "Visual Output Content Moderation",
"description": "Enable content moderation on output visual",
"default": false
}
},
"type": "object",
"required": [
"image"
],
"title": "BriaUpscaleImageRequest",
"description": "Request model for BRIA Increase Resolution."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/google-vision/image/editing-generation/inpaint¶
Imagen Inpainting
Description
Perform inpainting operations (insert or remove content from an image).
Args:
- operation_type : Type of inpainting operation ('insert' or 'remove')
prefer using semantic class for inpaint remove for best results.
- image_url : URL of the base image.
- prompt (optional): Text prompt describing what to insert (required for
'insert' operation, null prompt for 'remove' operation).
- mask_mode (optional): How to apply the mask (required for 'insert'
operation):
- MASK_MODE_FOREGROUND (FOREGROUND): Mask the foreground objects
- MASK_MODE_BACKGROUND (BACKGROUND): Mask the background
- MASK_MODE_SEMANTIC (SEMANTIC): Mask based on semantic classes
- MASK_MODE_USER_PROVIDED (USER_PROVIDED): Use a user-provided mask
- mask_dilation (optional, float): How much to dilate the mask (0.0-1.0,
required for 'insert' operation).
- removal_mode (optional): Method used for operation_type 'remove' can
either be 'semantic' or 'prompt' ('semantic' requires
'segmentation_classes', default is 'prompt', the prompt is always set to
empty).
- segmentation_classes (optional, list[int]): Segmentation class IDs
(required for semantic operations). The supported classes are available at
https://cloud.google.com/vertex-ai/generative-ai/docs/model-
reference/imagen-api-customization?hl=fr#segment-ids
Returns: - Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"operation_type": "insert",
"image_url": "string",
"prompt": null,
"mask_mode": null,
"mask_dilation": null,
"removal_mode": null,
"segmentation_classes": null,
"safety_filter_level": "BLOCK_LOW_AND_ABOVE",
"person_generation": "DONT_ALLOW"
}
Schema of the request body
{
"properties": {
"operation_type": {
"type": "string",
"enum": [
"insert",
"remove"
],
"title": "Operation Type",
"description": "Type of inpainting operation",
"examples": [
"insert",
"remove"
]
},
"image_url": {
"type": "string",
"minLength": 1,
"format": "uri",
"title": "Image Url",
"description": "URL of the base image",
"examples": [
"https://images.pexels.com/photos/29023629/pexels-photo-29023629.jpeg"
]
},
"prompt": {
"anyOf": [
{
"type": "string",
"minLength": 3
},
{
"type": "null"
}
],
"title": "Prompt",
"description": "Text prompt for insert operations",
"examples": [
"Add a tree to the left side"
]
},
"mask_mode": {
"anyOf": [
{
"$ref": "#/components/schemas/MaskReferenceMode"
},
{
"type": "null"
}
],
"description": "Masking mode for insert operations",
"examples": [
"MASK_MODE_FOREGROUND",
"MASK_MODE_BACKGROUND",
"MASK_MODE_SEMANTIC",
"MASK_MODE_USER_PROVIDED"
]
},
"mask_dilation": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Mask Dilation",
"description": "Mask dilation amount",
"default": 0.1
},
"removal_mode": {
"anyOf": [
{
"$ref": "#/components/schemas/RemovalMode"
},
{
"type": "null"
}
],
"description": "Removal mode for remove operations",
"default": "prompt",
"examples": [
"semantic",
"prompt"
]
},
"segmentation_classes": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Segmentation Classes",
"description": "Segmentation class IDs for semantic operations",
"examples": [
[
1,
2,
3
]
]
},
"safety_filter_level": {
"$ref": "#/components/schemas/SafetyFilterLevel",
"description": "Content safety filtering level",
"default": "BLOCK_MEDIUM_AND_ABOVE"
},
"person_generation": {
"$ref": "#/components/schemas/google__genai__types__PersonGeneration",
"description": "Person generation policy",
"default": "ALLOW_ALL"
}
},
"type": "object",
"required": [
"operation_type",
"image_url"
],
"title": "ImagenInpaintingRequest",
"description": "Request model for Imagen inpainting operations."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/google-vision/image/editing-generation/expand-image¶
Imagen Expand Image
Description
Expand an image by adding content around the edges (outpainting) using Google Imagen.
This endpoint uses the advanced ImageScaler system for precise positioning and supports both predefined positions and custom padding percentages for flexible image placement.
Args: - image_url: URL of the source image to expand - prompt: Text description of content to add around the edges - target_width (optional): Target width for the expanded image (500-4000px, default: 2500) - target_height (optional): Target height for the expanded image (500-4000px, default: 2500) - number_of_images (optional): Number of expanded variations to generate (1-4, default: 1) - mask_dilation (optional): Mask dilation for smoother blending (0.0-1.0, default: 0.03)
Positioning Options (choose one approach):
Option 1 - Predefined Position:
- position (optional): Predefined positioning. Options:
- center_vertical: Equal padding on all sides
- center_horizontal: Equal padding on all sides
- left_center: More padding on the left side
- right_center: More padding on the right side
- upper_left: Padding on right and bottom
- upper_center: Padding on bottom
- upper_right: Padding on left and bottom
- bottom_left: Padding on right and top
- bottom_center: Padding on top
- bottom_right: Padding on left and top
Option 2 - Custom Padding (all four values required if using): - padding_left (optional): Percentage of left padding (0.0-1.0) - padding_right (optional): Percentage of right padding (0.0-1.0) - padding_top (optional): Percentage of top padding (0.0-1.0) - padding_bottom (optional): Percentage of bottom padding (0.0-1.0)
Examples:
1. Center positioning (default):
{
"image_url": "https://images.pexels.com/photos/29023629/pexels-
photo-29023629.jpeg",
"prompt": "beautiful mountain landscape",
"target_width": 2000,
"target_height": 2000,
"position": "center_vertical"
}
2. Bottom center positioning for sky expansion:
{
"image_url": "https://images.pexels.com/photos/29023629/pexels-
photo-29023629.jpeg",
"prompt": "dramatic cloudy sky",
"position": "bottom_left"
}
3. Custom padding for precise control:
{
"image_url": "https://images.pexels.com/photos/29023629/pexels-
photo-29023629.jpeg",
"prompt": "forest environment",
"padding_left": 0.1,
"padding_right": 0.1,
"padding_top": 0.3,
"padding_bottom": 0.1
}
Returns: - Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image_url": "string",
"prompt": "string",
"target_width": 0,
"target_height": 0,
"number_of_images": 0,
"mask_dilation": 10.12,
"position": null,
"padding_left": null,
"padding_right": null,
"padding_top": null,
"padding_bottom": null,
"safety_filter_level": "BLOCK_LOW_AND_ABOVE",
"person_generation": "DONT_ALLOW"
}
Schema of the request body
{
"properties": {
"image_url": {
"type": "string",
"minLength": 1,
"format": "uri",
"title": "Image Url",
"description": "URL of the source image",
"examples": [
"https://images.pexels.com/photos/627678/pexels-photo-627678.jpeg"
]
},
"prompt": {
"type": "string",
"minLength": 3,
"title": "Prompt",
"description": "Description of content to add around edges",
"examples": [
"beautiful mountain landscape",
"dramatic cloudy sky"
]
},
"target_width": {
"type": "integer",
"maximum": 4000.0,
"minimum": 500.0,
"title": "Target Width",
"description": "Target width for expanded image",
"default": 2500
},
"target_height": {
"type": "integer",
"maximum": 4000.0,
"minimum": 500.0,
"title": "Target Height",
"description": "Target height for expanded image",
"default": 2500
},
"number_of_images": {
"type": "integer",
"maximum": 4.0,
"minimum": 1.0,
"title": "Number Of Images",
"description": "Number of expanded variations",
"default": 1
},
"mask_dilation": {
"type": "number",
"maximum": 1.0,
"minimum": 0.0,
"title": "Mask Dilation",
"description": "Mask dilation for smoother blending",
"default": 0.03
},
"position": {
"anyOf": [
{
"$ref": "#/components/schemas/ManualPlacement"
},
{
"type": "null"
}
],
"description": "Image positioning for automatic mode",
"examples": [
"center_horizontal",
"center_vertical"
]
},
"padding_left": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Padding Left",
"description": "Percentage of left padding to add",
"examples": [
0.1,
0.3
]
},
"padding_right": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Padding Right",
"description": "Percentage of right padding to add",
"examples": [
0.1,
0.3
]
},
"padding_top": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Padding Top",
"description": "Percentage of top padding to add",
"examples": [
0.3,
0.1
]
},
"padding_bottom": {
"anyOf": [
{
"type": "number",
"maximum": 1.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Padding Bottom",
"description": "Percentage of bottom padding to add",
"examples": [
0.1,
0.3
]
},
"safety_filter_level": {
"$ref": "#/components/schemas/SafetyFilterLevel",
"description": "Content safety filtering level",
"default": "BLOCK_MEDIUM_AND_ABOVE"
},
"person_generation": {
"$ref": "#/components/schemas/google__genai__types__PersonGeneration",
"description": "Person generation policy",
"default": "ALLOW_ALL"
}
},
"type": "object",
"required": [
"image_url",
"prompt"
],
"title": "ImagenExpandImageRequest",
"description": "Request model for Imagen image expansion (outpainting)."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/google-vision/image/editing-generation/generate-background¶
Imagen Generate Background
Description
Generate a new background for an image while preserving the foreground.
Args: - image_url : URL or path to the source image. - prompt : Description of the new background to generate. - seed (optional): Random seed for reproducibility. - number_of_images (optional): Number of variations to generate.
Returns: - Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image_url": "string",
"prompt": "string",
"number_of_images": 0,
"seed": null,
"safety_filter_level": "BLOCK_LOW_AND_ABOVE",
"person_generation": "DONT_ALLOW"
}
Schema of the request body
{
"properties": {
"image_url": {
"type": "string",
"minLength": 1,
"format": "uri",
"title": "Image Url",
"description": "URL of the source image",
"examples": [
"https://images.pexels.com/photos/627678/pexels-photo-627678.jpeg"
]
},
"prompt": {
"type": "string",
"minLength": 3,
"title": "Prompt",
"description": "Description of the desired background",
"examples": [
"Beautiful sunset over icy mountains",
"Dramatic cloudy sky over beach"
]
},
"number_of_images": {
"type": "integer",
"maximum": 4.0,
"minimum": 1.0,
"title": "Number Of Images",
"description": "Number of background variations",
"default": 1
},
"seed": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Seed",
"description": "Random seed for reproducible results (auto-generated if not provided)"
},
"safety_filter_level": {
"$ref": "#/components/schemas/SafetyFilterLevel",
"description": "Content safety filtering level",
"default": "BLOCK_MEDIUM_AND_ABOVE"
},
"person_generation": {
"$ref": "#/components/schemas/google__genai__types__PersonGeneration",
"description": "Person generation policy",
"default": "ALLOW_ALL"
}
},
"type": "object",
"required": [
"image_url",
"prompt"
],
"title": "ImagenBackgroundRequest",
"description": "Request model for Imagen background generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/google-vision/image/editing-generation/edit-image¶
Gemini Edit Image
Description
Edit images using text prompts with Gemini 2.0 Flash.
Supports both single-step editing and multi-turn sequential editing for complex transformations.
Args:
- image_url: URL of the source image to edit. Supports HTTP/HTTPS URLs
and GCS URIs (gs://).
- edit_prompt (optional): Text description of desired edits for single-
step editing.
- edit_steps (optional): Comma-separated list of edit prompts for multi-
turn sequential editing.
- safety_method (optional): Safety method for the image generation.
Options:
- PROBABILITY : Use probability-based safety
- SEVERITY : Use severity-based safety
- HARM_BLOCK_METHOD_UNSPECIFIED : Use harm block method
- safety_category (optional): Safety category for the image generation.
Options:
- HARM_CATEGORY_UNSPECIFIED : Unspecified safety category
- HARM_CATEGORY_HATE_SPEECH: Hate speech category
- HARM_CATEGORY_DANGEROUS_CONTENT: Dangerous content category
- HARM_CATEGORY_HARASSMENT: Harassment category
- HARM_CATEGORY_SEXUALLY_EXPLICIT: Sexually explicit content category
- HARM_CATEGORY_CIVIC_INTEGRITY: Civic integrity category
- safety_threshold (optional): Safety threshold for the image
generation. Options:
- HARM_BLOCK_THRESHOLD_UNSPECIFIED : Unspecified safety threshold
- BLOCK_LOW_AND_ABOVE (BLOCK_LOW_AND_ABOVE): Low and above threshold
- BLOCK_MEDIUM_AND_ABOVE (BLOCK_MEDIUM_AND_ABOVE): Medium and above
threshold
- BLOCK_ONLY_HIGH (BLOCK_ONLY_HIGH): Only high threshold
- BLOCK_NONE (BLOCK_NONE): No threshold
- OFF (OFF): Off threshold
Note: Provide either edit_prompt OR edit_steps, not both.
Examples:
1. Single edit:
{
"image_url":
"https://upload.wikimedia.org/wikipedia/commons/thumb/b/bf/Mona_Lisa-
restored.jpg/800px-Mona_Lisa-restored.jpg",
"edit_prompt": "Add sunglasses and change the background to a beach scene"
}
2. Multi-turn editing:
{
"image_url": "https://images.pexels.com/photos/36478/amazing-beautiful-
beauty-blue.jpg",
"edit_steps": "Add dramatic clouds to the sky, Increase saturation, Add a
rainbow"
}
3. Using GCS URI:
{
"image_url": "gs://cloud-samples-data/generative-ai/image/mirror.png",
"edit_prompt": "Convert to black and white and add vintage film grain
effect"
}
Returns: - Json response with success status and the result containing edited image URLs. For multi-turn editing, returns URLs for each step in the editing sequence.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image_url": "string",
"edit_prompt": null,
"edit_steps": null,
"safety_method": null,
"safety_category": null,
"safety_threshold": null
}
Schema of the request body
{
"properties": {
"image_url": {
"type": "string",
"minLength": 1,
"format": "uri",
"title": "Image Url",
"description": "URL of the source image to edit",
"examples": [
"https://upload.wikimedia.org/wikipedia/commons/thumb/b/bf/Mona_Lisa-restored.jpg/800px-Mona_Lisa_restored.jpg",
"https://images.pexels.com/photos/36478/amazing-beautiful-beauty-blue.jpg"
]
},
"edit_prompt": {
"anyOf": [
{
"type": "string",
"minLength": 3
},
{
"type": "null"
}
],
"title": "Edit Prompt",
"description": "Text description of desired edits (for single edit)",
"examples": [
"Add sunglasses and change the background to a beach scene",
"Convert to black and white and add vintage film grain effect"
]
},
"edit_steps": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Edit Steps",
"description": "Comma-separated list of edit prompts to apply sequentially (for multi-turn editing)",
"examples": [
"Add dramatic clouds to the sky, Increase saturation, Add a rainbow"
]
},
"safety_method": {
"anyOf": [
{
"$ref": "#/components/schemas/HarmBlockMethod"
},
{
"type": "null"
}
],
"description": "Safety filtering method",
"examples": [
"PROBABILITY",
"SEVERITY"
]
},
"safety_category": {
"anyOf": [
{
"$ref": "#/components/schemas/HarmCategory"
},
{
"type": "null"
}
],
"description": "Safety category to filter",
"examples": [
"HARM_CATEGORY_UNSPECIFIED",
"HARM_CATEGORY_HATE_SPEECH",
"HARM_CATEGORY_DANGEROUS_CONTENT",
"HARM_CATEGORY_HARASSMENT",
"HARM_CATEGORY_SEXUALLY_EXPLICIT",
"HARM_CATEGORY_CIVIC_INTEGRITY"
]
},
"safety_threshold": {
"anyOf": [
{
"$ref": "#/components/schemas/HarmBlockThreshold"
},
{
"type": "null"
}
],
"description": "Safety threshold level",
"examples": [
"BLOCK_LOW_AND_ABOVE",
"BLOCK_MEDIUM_AND_ABOVE",
"BLOCK_ONLY_HIGH",
"BLOCK_NONE"
]
}
},
"type": "object",
"required": [
"image_url"
],
"title": "GeminiEditImageRequest",
"description": "Request model for Gemini image editing."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/openai/image/editing-generation/edit-image¶
Gpt Generate Edit
Description
Generate an edit for an image using GPT Image API.
Args:
- request: GPT image editing request containing:
- prompt: The prompt for the image edit.
- image_url: URL of the image to be edited.
- number_of_images: Number of edited images to generate (1-10).
- size: Output image size.
- access_token: API key for authentication.
- gpt_image_client: GPTImageAPI client instance.
Returns: Json response with success status and the result containing the edited image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"prompt": {
"type": "string",
"minLength": 3,
"title": "Prompt",
"description": "Text description for the image edit",
"examples": [
"Add warm sunset tones and enhance contrast"
]
},
"image_url": {
"type": "string",
"minLength": 1,
"format": "uri",
"title": "Image Url",
"description": "URL of the image to be edited",
"examples": [
"https://images.pexels.com/photos/29023629/pexels-photo-29023629.jpeg"
]
},
"number_of_images": {
"type": "integer",
"maximum": 10.0,
"minimum": 1.0,
"title": "Number Of Images",
"description": "Number of edited images to generate",
"default": 1
},
"aspect_ratio": {
"type": "string",
"enum": [
"1:1",
"2:3",
"3:2"
],
"title": "Aspect Ratio",
"description": "Desired aspect ratio",
"default": "1:1"
}
},
"type": "object",
"required": [
"prompt",
"image_url"
],
"title": "GPTEditImageRequest",
"description": "Request model for GPT image editing."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/openai/image/editing-generation/inpaint¶
Gpt Image Inpainting
Description
Edit an image using a mask with GPT Image API. You can provide a mask to indicate where the image should be edited. The transparent areas of the mask will be replaced, while the filled areas will be left unchanged.
This endpoint supports two inpainting modes: 1. Manual Mask Mode: Use your own mask image to specify exact areas to edit 2. Border-Only Mode: Automatically generate a border mask for edge inpainting
Args:
- request: GPT inpainting request containing:
- prompt: Text description of the desired edited image
- image_url: URL or file path of the source image (either this or image_file required)
- image_file: Base64 encoded source image (either this or image_url required)
- mask_url: URL or file path of the mask image (required unless inpaint_border_only is True)
- mask_file: Base64 encoded mask image (required unless inpaint_border_only is True)
- inpaint_border_only: Whether to inpaint only the border areas (default: False)
- border_percentage: Percentage of border to inpaint when using border- only mode
- access_token: API key for authentication
- gpt_image_client: GPTImageAPI client instance.
- Examples:
- 1. Manual Mask with URLs: ```json {
- "prompt": "beautiful flowers in the garden",
- "image_url": "https://images.pexels.com/photos/29023629/pexels- photo-29023629.jpeg",
- "mask_url": "https://example.com/mask.png",
- "inpaint_border_only": false } ```
- 2. Border-Only Inpainting: ```json {
- "prompt": "expand with forest environment",
- "image_url": "https://images.pexels.com/photos/29023629/pexels- photo-29023629.jpeg",
- "inpaint_border_only": true,
- "border_percentage": 0.2 } ```
Returns: Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"prompt": "string",
"image_url": null,
"image_file": null,
"mask_url": null,
"mask_file": null,
"inpaint_border_only": true,
"border_percentage": 10.12
}
Schema of the request body
{
"properties": {
"prompt": {
"type": "string",
"minLength": 3,
"title": "Prompt",
"description": "Text description of the desired edit",
"examples": [
"beautiful flowers in the garden",
"expand with forest environment"
]
},
"image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Image Url",
"description": "URL of input image",
"examples": [
"https://images.pexels.com/photos/29023629/pexels-photo-29023629.jpeg"
]
},
"image_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Image File",
"description": "Base64 encoded input image",
"examples": [
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA..."
]
},
"mask_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Mask Url",
"description": "URL of mask image",
"examples": [
"https://example.com/mask.png"
]
},
"mask_file": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Mask File",
"description": "Base64 encoded mask image",
"examples": [
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA..."
]
},
"inpaint_border_only": {
"type": "boolean",
"title": "Inpaint Border Only",
"description": "Whether to inpaint only border areas",
"default": false
},
"border_percentage": {
"type": "number",
"maximum": 0.5,
"minimum": 0.01,
"title": "Border Percentage",
"description": "Percentage of border to inpaint when using border-only mode",
"default": 0.05,
"examples": [
0.05,
0.2,
0.3
]
}
},
"type": "object",
"required": [
"prompt"
],
"title": "GPTInpaintingRequest",
"description": "Request model for GPT image inpainting."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/firefly/image/editing-generation/generate-product-background¶
Generate Object Composite Async
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"prompt": "string",
"image": {
"source": {
"upload_id": null,
"url": null
}
},
"mask": null,
"content_class": "photo",
"placement": {
"alignment": {
"horizontal": "center",
"vertical": "center"
},
"insert": {
"center": 0,
"top": 0,
"bottom": 0,
"left": 0,
"right": 0
}
},
"seeds": null,
"size": {
"height": 0,
"width": 0
},
"style": null
}
Schema of the request body
{
"properties": {
"prompt": {
"type": "string",
"title": "Prompt"
},
"image": {
"$ref": "#/components/schemas/ImageReferenceModel"
},
"mask": {
"$ref": "#/components/schemas/ImageReferenceModel"
},
"content_class": {
"$ref": "#/components/schemas/ContentClass",
"default": "photo"
},
"placement": {
"$ref": "#/components/schemas/PlacementModel",
"default": {
"alignment": {
"horizontal": "center",
"vertical": "center"
},
"insert": {
"bottom": 0,
"center": 0,
"left": 0,
"right": 0,
"top": 0
}
}
},
"seeds": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Seeds"
},
"size": {
"$ref": "#/components/schemas/SizeImagesAsyncModel",
"default": {
"height": 2048,
"width": 2048
}
},
"style": {
"anyOf": [
{
"$ref": "#/components/schemas/StyleModel"
},
{
"type": "null"
}
]
}
},
"type": "object",
"required": [
"prompt",
"image",
"mask"
],
"title": "Body_generate_object_composite_async_api_v1_firefly_image_editing_generation_generate_product_background_post"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/firefly/image/editing-generation/expand-image¶
Expand Image Async
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image": {
"source": {
"upload_id": null,
"url": null
}
},
"mask": {
"invert": true,
"source": null
},
"placement": {
"alignment": {
"horizontal": "center",
"vertical": "center"
},
"insert": {
"center": 0,
"top": 0,
"bottom": 0,
"left": 0,
"right": 0
}
},
"prompt": null,
"seeds": null,
"size": {
"height": 0,
"width": 0
}
}
Schema of the request body
{
"properties": {
"image": {
"$ref": "#/components/schemas/ImageReferenceModel"
},
"mask": {
"$ref": "#/components/schemas/MaskModel"
},
"placement": {
"$ref": "#/components/schemas/PlacementModel",
"default": {
"alignment": {
"horizontal": "center",
"vertical": "center"
},
"insert": {
"bottom": 0,
"center": 0,
"left": 0,
"right": 0,
"top": 0
}
}
},
"prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Prompt"
},
"seeds": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Seeds"
},
"size": {
"$ref": "#/components/schemas/SizeImagesAsyncModel",
"default": {
"height": 2048,
"width": 2048
}
}
},
"type": "object",
"required": [
"image",
"mask"
],
"title": "Body_expand_image_async_api_v1_firefly_image_editing_generation_expand_image_post"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/firefly/image/editing-generation/inpaint¶
Fill Image Async
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"image": {
"source": {
"upload_id": null,
"url": null
}
},
"mask": {
"invert": true,
"source": null
},
"negative_prompt": null,
"prompt": null,
"prompt_biasing_locale_code": null,
"seeds": null,
"size": {
"height": 0,
"width": 0
}
}
Schema of the request body
{
"properties": {
"image": {
"$ref": "#/components/schemas/ImageReferenceModel"
},
"mask": {
"$ref": "#/components/schemas/MaskModel"
},
"negative_prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Negative Prompt"
},
"prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Prompt"
},
"prompt_biasing_locale_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Prompt Biasing Locale Code"
},
"seeds": {
"anyOf": [
{
"items": {
"type": "integer"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Seeds"
},
"size": {
"$ref": "#/components/schemas/SizeImagesAsyncModel",
"default": {
"height": 2048,
"width": 2048
}
}
},
"type": "object",
"required": [
"image",
"mask"
],
"title": "Body_fill_image_async_api_v1_firefly_image_editing_generation_inpaint_post"
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Video Editing¶
POST /api/v1/bria/video/editing/remove-background¶
Bria Video Remove Background
Description
Remove background from a video.
Args:
- video_url: URL of input video.
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Returns: Json response with success status and the result containing the generated image URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"video": {
"type": "string",
"minLength": 1,
"format": "uri",
"title": "Video",
"description": "Publicly accessible URL of the input video. Input resolution supported up to 16000x16000 (16K)",
"examples": [
"https://example.com/video.mp4"
]
},
"background_color": {
"anyOf": [
{
"type": "string",
"enum": [
"Transparent",
"Black",
"White",
"Gray",
"Red",
"Green",
"Blue",
"Yellow",
"Cyan",
"Magenta",
"Orange"
]
},
{
"type": "null"
}
],
"title": "Background Color",
"description": "Predefined string only - hex values are not supported",
"default": "Transparent"
},
"output_container_and_codec": {
"anyOf": [
{
"type": "string",
"enum": [
"mp4_h264",
"mp4_h265",
"webm_vp9",
"mov_h265",
"mov_proresks",
"mkv_h264",
"mkv_h265",
"mkv_vp9",
"mkv_raw",
"gif",
"avi_h264"
]
},
{
"type": "null"
}
],
"title": "Output Container And Codec",
"description": "Output container and codec preset",
"default": "webm_vp9"
}
},
"type": "object",
"required": [
"video"
],
"title": "BriaVideoRemoveBackgroundRequest",
"description": "Request model for BRIA Video Background Removal."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Status¶
GET /api/v1/bria/status/{task_id}¶
Bria Get Status
Description
Get the status of an asynchronous Bria request.
Args:
- task_id: Unique identifier of the request.
- access_token: API key for authentication.
- bria_client: BriaAPI client.
Returns: Json response containing: - status: Current status (IN_PROGRESS, COMPLETED, ERROR, UNKNOWN) - task_id: The request identifier - result (when COMPLETED): Contains image_url and optionally seed, prompt, refined_prompt - error (when ERROR): Contains message and optional error code
HTTP Status Codes: - 200: Normal operation (check status field for actual job status) - 404: Request ID not found or expired - 5XX: Status service internal error
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
task_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"properties": {
"status": {
"type": "string",
"enum": [
"IN_PROGRESS",
"COMPLETED",
"ERROR",
"UNKNOWN"
],
"title": "Status",
"description": "Current status of the request"
},
"request_id": {
"type": "string",
"title": "Request Id",
"description": "Unique identifier of the request"
},
"result": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"title": "Result",
"description": "Result object when status is COMPLETED (contains image_url, seed, prompt, refined_prompt)"
},
"error": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"title": "Error",
"description": "Error object when status is ERROR (contains message and optional code)"
}
},
"type": "object",
"required": [
"status",
"request_id"
],
"title": "BriaStatusResponse",
"description": "Response model for Bria status endpoint."
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
GET /api/v1/firefly/status/{task_id}¶
Get Result
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
task_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
DELETE /api/v1/firefly/cancel/{task_id}¶
Cancel Job
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
task_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
GET /api/v1/runway/status/{task_id}¶
Fetch Task Details
Description
Fetch the details of a task by its task ID. This endpoint retrieves the current status and metadata of a previously submitted task (e.g., image or video generation) using its unique task ID.
Args:
- task_id: The unique identifier of the RunwayML task.
Returns: Json response with success status and the result containing the generated image URLs and metadata.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
task_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
DELETE /api/v1/runway/cancel/{task_id}¶
Delete Task
Description
Delete a task by its task ID. This endpoint allows you to cancel or delete a previously submitted task (such as image or video generation) using its unique task ID.
Args:
- task_id: The unique identifier of the RunwayML task to be deleted.
Returns: Json response with status message or any error details if the task could not be deleted.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
task_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
LoRA Project Management¶
GET /api/v1/bria-lora/projects¶
Get All Projects
Description
Get all LoRA projects. Returns: - JSONResponse: List of all projects
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
POST /api/v1/bria-lora/projects¶
Create Project
Description
Create a new LoRA project. Args:
- project_name: Name of the project
- ip_medium: Medium of the IP (e.g., photography, illustration)
- ip_type: Type of the IP (e.g., multi_object_set, object_variants, defined_character, style)
- project_description: Description of the project
- ip_name: Name of the IP (required for defined_character)
- ip_description: Description of the IP
Returns: - JSONResponse: Response containing the created project details
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"project_name": "string",
"ip_medium": "photography",
"ip_type": "multi_object_set",
"project_description": null,
"ip_name": null,
"ip_description": null
}
Schema of the request body
{
"properties": {
"project_name": {
"type": "string",
"maxLength": 255,
"minLength": 1,
"title": "Project Name",
"description": "Name of the project"
},
"ip_medium": {
"type": "string",
"enum": [
"photography",
"illustration"
],
"title": "Ip Medium",
"description": "Medium of the IP"
},
"ip_type": {
"type": "string",
"enum": [
"multi_object_set",
"object_variants",
"defined_character",
"style"
],
"title": "Ip Type",
"description": "Type of the IP"
},
"project_description": {
"anyOf": [
{
"type": "string",
"maxLength": 1000
},
{
"type": "null"
}
],
"title": "Project Description",
"description": "Description of the project"
},
"ip_name": {
"anyOf": [
{
"type": "string",
"maxLength": 255
},
{
"type": "null"
}
],
"title": "Ip Name",
"description": "Name of the IP (required for defined_character)"
},
"ip_description": {
"anyOf": [
{
"type": "string",
"maxLength": 1000
},
{
"type": "null"
}
],
"title": "Ip Description",
"description": "Description of the IP"
}
},
"type": "object",
"required": [
"project_name",
"ip_medium",
"ip_type"
],
"title": "BriaLoraCreateProjectRequest",
"description": "Request model for creating a Bria Lora project."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
GET /api/v1/bria-lora/projects/{project_id}¶
Get Project
Description
Get a specific LoRA project by ID. Args:
- project_id: ID of the project to retrieve
Returns: - JSONResponse: Project details
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
project_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
PUT /api/v1/bria-lora/projects/{project_id}¶
Update Project
Description
Update a LoRA project. Args:
- project_id: ID of the project to update
- project_name: New name of the project
- project_description: New description of the project
- ip_name: New name of the IP
- ip_description: New description of the IP
Returns: - JSONResponse: Response containing the updated project details
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
project_id |
path | string | No |
Request body
{
"project_id": 0,
"project_name": null,
"project_description": null,
"ip_name": null,
"ip_description": null
}
Schema of the request body
{
"properties": {
"project_id": {
"type": "integer",
"exclusiveMinimum": 0.0,
"title": "Project Id",
"description": "ID of the project to update"
},
"project_name": {
"anyOf": [
{
"type": "string",
"maxLength": 255,
"minLength": 1
},
{
"type": "null"
}
],
"title": "Project Name",
"description": "New project name"
},
"project_description": {
"anyOf": [
{
"type": "string",
"maxLength": 1000
},
{
"type": "null"
}
],
"title": "Project Description",
"description": "New project description"
},
"ip_name": {
"anyOf": [
{
"type": "string",
"maxLength": 255
},
{
"type": "null"
}
],
"title": "Ip Name",
"description": "New IP name"
},
"ip_description": {
"anyOf": [
{
"type": "string",
"maxLength": 1000
},
{
"type": "null"
}
],
"title": "Ip Description",
"description": "New IP description"
}
},
"type": "object",
"required": [
"project_id"
],
"title": "BriaLoraUpdateProjectRequest",
"description": "Request model for updating a Bria Lora project."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
DELETE /api/v1/bria-lora/projects/{project_id}¶
Delete Project
Description
Delete a LoRA project. Args:
- project_id: ID of the project to delete
Returns: - JSONResponse: Confirmation of deletion
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
project_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
GET /api/v1/bria-lora/datasets¶
Get All Datasets
Description
Get all datasets. Returns: - JSONResponse: List of all datasets
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
POST /api/v1/bria-lora/datasets¶
Create Dataset
Description
Create a new dataset in a LoRA project. Args:
- project_id: ID of the project to which the dataset belongs
- name: Name of the dataset
Returns: - JSONResponse: Response containing the created dataset details
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"project_id": {
"type": "integer",
"exclusiveMinimum": 0.0,
"title": "Project Id",
"description": "ID of the project"
},
"name": {
"type": "string",
"maxLength": 255,
"minLength": 1,
"title": "Name",
"description": "Name of the dataset"
}
},
"type": "object",
"required": [
"project_id",
"name"
],
"title": "BriaLoraCreateDatasetRequest",
"description": "Request model for creating a dataset."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
GET /api/v1/bria-lora/datasets/{dataset_id}¶
Get Dataset
Description
Get a specific dataset by ID. Args:
- dataset_id: ID of the dataset to retrieve
Returns: - JSONResponse: Dataset details
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
dataset_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
PUT /api/v1/bria-lora/datasets/{dataset_id}¶
Update Dataset
Description
Update a dataset. Args:
- dataset_id: ID of the dataset to update
- name: New name of the dataset
- caption_prefix: Optional prefix for captions
- status: Status of the dataset (draft or completed)
Returns: - JSONResponse: Response containing the updated dataset details
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
dataset_id |
path | string | No |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"dataset_id": {
"type": "integer",
"exclusiveMinimum": 0.0,
"title": "Dataset Id",
"description": "ID of the dataset to update"
},
"name": {
"anyOf": [
{
"type": "string",
"maxLength": 255,
"minLength": 1
},
{
"type": "null"
}
],
"title": "Name",
"description": "New dataset name"
},
"caption_prefix": {
"anyOf": [
{
"type": "string",
"maxLength": 255
},
{
"type": "null"
}
],
"title": "Caption Prefix",
"description": "New caption prefix"
},
"status": {
"anyOf": [
{
"type": "string",
"enum": [
"draft",
"completed"
]
},
{
"type": "null"
}
],
"title": "Status",
"description": "New status"
}
},
"type": "object",
"required": [
"dataset_id"
],
"title": "BriaLoraUpdateDatasetRequest",
"description": "Request model for updating a dataset."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
DELETE /api/v1/bria-lora/datasets/{dataset_id}¶
Delete Dataset
Description
Delete a dataset. Args:
- dataset_id: ID of the dataset to delete
Returns: - JSONResponse: Confirmation of deletion
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
dataset_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
GET /api/v1/bria-lora/projects/{project_id}/datasets¶
Get Project Datasets
Description
Get all datasets for a specific project. Args:
- project_id: ID of the project
- include_models: Include full model objects (default: False)
- include_models_ids: Include model IDs (default: False)
Returns: - JSONResponse: List of datasets for the project
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
include_models |
query | boolean | False | No | |
include_models_ids |
query | boolean | False | No | |
project_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria-lora/datasets/{dataset_id}/images¶
Upload Image
Description
Upload an image to a dataset in a LoRA project. The image can be uploaded via file path or URL. Args:
- dataset_id: ID of the dataset to upload the image to
- file_path: Path to the image file (optional)
- image_url: URL of the image (optional)
- image_name: Name of the image (optional)
Returns: - JSONResponse: Response containing the result of the upload operation
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
dataset_id |
path | string | No |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"dataset_id": {
"type": "integer",
"exclusiveMinimum": 0.0,
"title": "Dataset Id",
"description": "ID of the dataset to upload the image to"
},
"file_path": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "File Path",
"description": "Path to the image file"
},
"image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Image Url",
"description": "URL of the image"
},
"image_name": {
"anyOf": [
{
"type": "string",
"maxLength": 255
},
{
"type": "null"
}
],
"title": "Image Name",
"description": "Name of the image"
}
},
"type": "object",
"required": [
"dataset_id"
],
"title": "BriaLoraUploadImageRequest",
"description": "Request model for uploading an image to a dataset."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
GET /api/v1/bria-lora/datasets/{dataset_id}/images¶
Get Dataset Images
Description
Get all images in a dataset. Args:
- dataset_id: ID of the dataset
Returns: - JSONResponse: List of images in the dataset
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
dataset_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
GET /api/v1/bria-lora/datasets/{dataset_id}/images/{image_id}¶
Get Dataset Image
Description
Get a specific image from a dataset. Args:
- dataset_id: ID of the dataset
- image_id: ID of the image
Returns: - JSONResponse: Image details
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
dataset_id |
path | string | No | ||
image_id |
path | integer | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
DELETE /api/v1/bria-lora/datasets/{dataset_id}/images/{image_id}¶
Delete Image
Description
Delete an image from a dataset. Args:
- dataset_id: ID of the dataset
- image_id: ID of the image to delete
Returns: - JSONResponse: Confirmation of deletion
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
dataset_id |
path | string | No | ||
image_id |
path | integer | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
PUT /api/v1/bria-lora/datasets/{dataset_id}/images/{image_id}/caption¶
Update Image Caption
Description
Update the caption of an image in a dataset. Optionally regenerate the caption using the model. Args:
- dataset_id: ID of the dataset containing the image
- image_id: ID of the image to update
- caption: New manual caption (optional)
- regenerate_caption: Whether to regenerate the caption automatically (default: False)
Returns: - JSONResponse: Response containing the result of the caption update operation
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
dataset_id |
path | string | No | ||
image_id |
path | integer | No |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"image_id": {
"type": "integer",
"exclusiveMinimum": 0.0,
"title": "Image Id",
"description": "ID of the image to update"
},
"dataset_id": {
"type": "integer",
"exclusiveMinimum": 0.0,
"title": "Dataset Id",
"description": "ID of the dataset containing the image"
},
"caption": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Caption",
"description": "New manual caption"
},
"regenerate_caption": {
"type": "boolean",
"title": "Regenerate Caption",
"description": "Whether to regenerate caption automatically",
"default": false
}
},
"type": "object",
"required": [
"image_id",
"dataset_id"
],
"title": "BriaLoraUpdateImageCaptionRequest",
"description": "Request model for updating image caption."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
PUT /api/v1/bria-lora/datasets/{dataset_id}/images/captions¶
Regenerate All Captions
Description
Regenerate captions for all images in a dataset. Args:
- dataset_id: ID of the dataset
Returns: - JSONResponse: Result of regeneration
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
dataset_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
GET /api/v1/bria-lora/models¶
Get All Models
Description
Get all models. Returns: - JSONResponse: List of all models
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
POST /api/v1/bria-lora/models¶
Create Model
Description
Create a new model in a LoRA project. Args:
- name: Name of the model
- dataset_id: ID of the dataset to use for training
- training_version: Training version (light or max)
- description: Description of the model
Returns: - JSONResponse: Response containing the created model details
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"name": {
"type": "string",
"maxLength": 255,
"minLength": 1,
"title": "Name",
"description": "Model name"
},
"dataset_id": {
"type": "integer",
"exclusiveMinimum": 0.0,
"title": "Dataset Id",
"description": "Dataset ID to use for training"
},
"training_version": {
"type": "string",
"enum": [
"light",
"max"
],
"title": "Training Version",
"description": "Training version"
},
"description": {
"anyOf": [
{
"type": "string",
"maxLength": 1000
},
{
"type": "null"
}
],
"title": "Description",
"description": "Model description"
}
},
"type": "object",
"required": [
"name",
"dataset_id",
"training_version"
],
"title": "BriaLoraCreateModelRequest",
"description": "Request model for creating a model."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
GET /api/v1/bria-lora/models/{model_id}¶
Get Model
Description
Get a specific model by ID. Args:
- model_id: ID of the model to retrieve
Returns: - JSONResponse: Model details
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
model_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
PUT /api/v1/bria-lora/models/{model_id}¶
Update Model
Description
Update a model. Args:
- model_id: ID of the model to update
- name: New name of the model
- description: New description of the model
Returns: - JSONResponse: Response containing the updated model details
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
model_id |
path | string | No |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"model_id": {
"type": "integer",
"exclusiveMinimum": 0.0,
"title": "Model Id",
"description": "ID of the model to update"
},
"name": {
"anyOf": [
{
"type": "string",
"maxLength": 255,
"minLength": 1
},
{
"type": "null"
}
],
"title": "Name",
"description": "New model name"
},
"description": {
"anyOf": [
{
"type": "string",
"maxLength": 1000
},
{
"type": "null"
}
],
"title": "Description",
"description": "New model description"
}
},
"type": "object",
"required": [
"model_id"
],
"title": "BriaLoraUpdateModelRequest",
"description": "Request model for updating a model."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
DELETE /api/v1/bria-lora/models/{model_id}¶
Delete Model
Description
Delete a model. Args:
- model_id: ID of the model to delete
Returns: - JSONResponse: Confirmation of deletion
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
model_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
GET /api/v1/bria-lora/projects/{project_id}/models¶
Get Project Models
Description
Get all models for a specific project. Args:
- project_id: ID of the project
Returns: - JSONResponse: List of models for the project
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
project_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
LoRA Training¶
POST /api/v1/bria-lora/models/{model_id}/training/start¶
Start Training
Description
Start training a model. Args:
- model_id: ID of the model to start training
Returns: - JSONResponse: Training status
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
model_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/bria-lora/models/{model_id}/training/stop¶
Stop Training
Description
Stop training a model. Args:
- model_id: ID of the model to stop training
Returns: - JSONResponse: Training status
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
model_id |
path | string | No |
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Video Generation¶
POST /api/v1/google-vision/video/generation/generate-video¶
Veo Generate Video
Description
Generate videos using Vertex AI VEO.
Args:
- prompt: Text description of the desired video
- start_image_url: Optional starting image URL for video generation
- number_of_videos: Number of videos to generate (1-4)
- aspect_ratio: Video aspect ratio. Options: "9:16" (PORTRAIT_9_16), "16:9" (LANDSCAPE_16_9)
- duration: Video duration in seconds. Options: 5 (SHORT), 10 (MEDIUM)
- person_generation: Person generation control. Options: "allow" (ALL), "allow_adult" (ADULT), "dont_allow" (NONE)
- enhance_prompt: Whether to enhance the input prompt using LLM
- prefix: Prefix for generated video files (default: "veo2_generations")
- access_token: Special VEO authentication token for video generation
- veo_client: VEO API client instance
Returns: Json response with success status and the result containing the generated video URLs.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"model": "veo-2.0-generate-001",
"prompt": "string",
"aspect_ratio": "9:16",
"duration": 0,
"start_image_url": null,
"person_generation": null,
"enhance_prompt": null,
"negative_prompt": null,
"seed": null
}
Schema of the request body
{
"properties": {
"model": {
"$ref": "#/components/schemas/VeoModel",
"description": "Model to use for video generation",
"default": "veo-2.0-generate-001"
},
"prompt": {
"type": "string",
"minLength": 4,
"title": "Prompt",
"description": "Text description of the desired video",
"examples": [
"A cinematic timelapse of a city skyline at dusk",
"A serene ocean wave crashing in slow motion"
]
},
"aspect_ratio": {
"type": "string",
"enum": [
"9:16",
"16:9"
],
"title": "Aspect Ratio",
"description": "Video aspect ratio",
"default": "16:9"
},
"duration": {
"$ref": "#/components/schemas/VeoDuration",
"description": "Video duration in seconds",
"default": 5
},
"start_image_url": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Start Image Url",
"description": "URL of starting image for video",
"examples": [
"https://images.pexels.com/photos/421927/pexels-photo-421927.jpeg",
"gs://bucket/path/to/starting_image.png"
]
},
"person_generation": {
"anyOf": [
{
"$ref": "#/components/schemas/src__models__veo__PersonGeneration"
},
{
"type": "null"
}
],
"description": "People generation controls",
"default": "allow"
},
"enhance_prompt": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Enhance Prompt",
"description": "Whether to enhance the input prompt",
"default": false
},
"negative_prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Negative Prompt",
"description": "Text description of what to avoid in the video",
"examples": [
"No text overlays",
"Avoid fast cuts and shaky camera"
]
},
"seed": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Seed",
"description": "Seed for video generation"
}
},
"type": "object",
"required": [
"prompt"
],
"title": "VeoGenerateVideoRequest",
"description": "Request model for VEO video generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/runway/video/generation/generate-video-from-text¶
Generate Video From Text
Description
Generate a video from a text prompt. This endpoint uses the VEO3 model to generate a video purely from a text description, without requiring any input images or videos.
Args:
- request (RunwayGenerateVideoFromTextRequest):
- prompt (str): Description of the desired video.
- model ("veo3"): Model variant.
- aspect_ratio ("1280:720" | "720:1280"): Output aspect ratio.
- duration (8): Video duration in seconds.
- seed (int | None): Seed for reproducible results.
Returns: Json response with success status and the result containing the response, including task ID, status, and result URL (if available), or any error details.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"prompt": {
"type": "string",
"maxLength": 1000,
"minLength": 1,
"title": "Prompt To Generate Video",
"description": "A non-empty string up to 1000 characters describing what should appear in the output.",
"examples": [
"Cinematic short video of a sleek black sports car driving smoothly on a snowy mountain road. The car kicks up snow powder as it speeds along the icy suface."
]
},
"model": {
"type": "string",
"const": "veo3",
"title": "Model Variant",
"description": "The model variant to use. Currently only veo3 is supported for text-to-video.",
"default": "veo3"
},
"aspect_ratio": {
"type": "string",
"enum": [
"1280:720",
"720:1280"
],
"title": "Aspect ratio",
"description": "A string representing the aspect ratio of the output video.",
"default": "1280:720"
},
"duration": {
"type": "integer",
"const": 8,
"title": "Duration",
"description": "Veo 3 videos must be 8 seconds long.",
"default": 8
},
"seed": {
"anyOf": [
{
"type": "integer",
"maximum": 4294967295.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Seed",
"description": "If unspecified, a random number is chosen. Varying the seed integer is a way to get different results."
}
},
"type": "object",
"required": [
"prompt"
],
"title": "RunwayGenerateVideoFromTextRequest",
"description": "Request model for Runway text to video generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/runway/video/generation/generate-video-from-image¶
Generate Video From Image
Description
Generate a video from an input image.
Args:
- request (RunwayGenerateVideoFromImageRequest):
- prompt (str): Description of the desired video.
- image_url (HttpUrl | None): Optional first-frame image.
- aspect_ratio (VideoAspectRatio): Output aspect ratio.
- duration (5 | 10): Video duration in seconds.
- model ("gen4_turbo" | "gen3a_turbo" | "veo3"): Model variant.
- seed (int | None): Seed for reproducible results.
- content_moderation (ContentModeration | None): Moderation settings (not for "veo3").
Returns: Json response with success status and the result containing the response, including task ID, status, and result URL (if available), or any error details.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"prompt": "string",
"image_url": null,
"aspect_ratio": "1280:720",
"duration": 0,
"model": "gen4_turbo",
"seed": null,
"content_moderation": null
}
Schema of the request body
{
"properties": {
"prompt": {
"type": "string",
"maxLength": 1000,
"minLength": 1,
"title": "Prompt To Generate Video",
"description": "A non-empty string up to 1000 characters describing what should appear in the output.",
"examples": [
"a man walking on the beach"
]
},
"image_url": {
"anyOf": [
{
"type": "string",
"maxLength": 2048,
"minLength": 1,
"format": "uri"
},
{
"type": "null"
}
],
"title": "Prompt Image",
"description": "HTTPS URL or data URI containing an encoded image to be used as the first frame of the generated video.",
"examples": [
"https://images.pexels.com/photos/21836744/pexels-photo-21836744.jpeg"
]
},
"aspect_ratio": {
"$ref": "#/components/schemas/VideoAspectRatio",
"title": "Aspect ratio",
"description": "The resolution of the output video.",
"default": "1280:720"
},
"duration": {
"type": "integer",
"enum": [
5,
10
],
"title": "Duration of Video",
"description": "The number of seconds of duration for the output video.",
"default": 10,
"examples": [
5,
10
]
},
"model": {
"type": "string",
"enum": [
"gen4_turbo",
"gen3a_turbo",
"veo3"
],
"title": "Model Variant",
"description": "The model variant to use for video generation.",
"default": "gen4_turbo"
},
"seed": {
"anyOf": [
{
"type": "integer",
"maximum": 4294967295.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Seed",
"description": "If unspecified, a random number is chosen. Varying the seed integer is a way to get different results."
},
"content_moderation": {
"anyOf": [
{
"$ref": "#/components/schemas/ContentModeration"
},
{
"type": "null"
}
],
"description": "Settings that affect the behavior of the content moderation system. Only allowed for gen4_turbo and gen3a_turbo models."
}
},
"type": "object",
"required": [
"prompt"
],
"title": "RunwayGenerateVideoFromImageRequest",
"description": "Request model for Runway image to video generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/runway/video/generation/generate-video-from-motion¶
Generate Video From Motion
Description
Generate a video from a reference video for motion and expression transfer.
Args:
- request (RunwayGenerateVideoFromMotionRequest):
- character (CharacterInput): {
type: "image" | "video",uri: HttpUrl}. - reference_url (HttpUrl): Reference performance video (3–30s).
- aspect_ratio (VideoAspectRatio): Output aspect ratio.
- body_control (bool): Enable non-facial movement transfer.
- expression_intensity (int 1–5): Expression intensity.
- seed (int | None): Seed for reproducible results.
- content_moderation (ContentModeration | None): Moderation settings.
Returns: Json response with success status and the result containing the response, including task ID, status, and result URL (if available), or any error details.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"character": {
"type": "image",
"uri": "string"
},
"reference_url": "string",
"aspect_ratio": "1280:720",
"body_control": true,
"expression_intensity": 0,
"seed": null,
"content_moderation": null
}
Schema of the request body
{
"properties": {
"character": {
"$ref": "#/components/schemas/CharacterInput",
"title": "Character",
"description": "The character to control. You can either provide a video or an image."
},
"reference_url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"format": "uri",
"title": "Reference Video URL",
"description": "HTTPS URL pointing to a video of a person performing in the manner that you would like your character to perform. The video must be between 3 and 30 seconds in duration.",
"examples": [
"https://sample-videos.com/zip/10/mp4/SampleVideo_1280x720_1mb.mp4"
]
},
"aspect_ratio": {
"$ref": "#/components/schemas/VideoAspectRatio",
"title": "Aspect ratio",
"description": "The resolution of the output video.",
"default": "1280:720"
},
"body_control": {
"type": "boolean",
"title": "Body Control",
"description": "A boolean indicating whether to enable body control. When enabled, non-facial movements and gestures will be applied to the character in addition to facial expressions.",
"default": true
},
"expression_intensity": {
"type": "integer",
"maximum": 5.0,
"minimum": 1.0,
"title": "Expression Intensity",
"description": "An integer between 1 and 5 (inclusive). A larger value increases the intensity of the character's expression.",
"default": 3
},
"seed": {
"anyOf": [
{
"type": "integer",
"maximum": 4294967295.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Seed",
"description": "If unspecified, a random number is chosen. Varying the seed integer is a way to get different results."
},
"content_moderation": {
"anyOf": [
{
"$ref": "#/components/schemas/ContentModeration"
},
{
"type": "null"
}
],
"description": "Settings that affect the behavior of the content moderation system."
}
},
"type": "object",
"required": [
"character",
"reference_url"
],
"title": "RunwayGenerateVideoFromMotionRequest",
"description": "Request model for Runway character performance (act-two model)."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
POST /api/v1/runway/video/generation/generate-video-from-video¶
Generate Video From Video
Description
Generate a new video based on a given input video and a reference image.
Args:
- request (RunwayGenerateVideoFromVideoRequest):
- prompt (str): Description of the desired transformation/styling.
- video_uri (HttpUrl): Source video (3–30s).
- reference_image_url (HttpUrl): Style reference image.
- aspect_ratio (VideoAspectRatio): Output aspect ratio.
- seed (int | None): Seed for reproducible results.
- content_moderation (ContentModeration | None): Moderation settings.
Returns: Json response with success status and the result containing the response, including task ID, status, and result URL (if available), or any error details.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
{
"prompt": "string",
"video_uri": "string",
"reference_image_url": "string",
"aspect_ratio": "1280:720",
"seed": null,
"content_moderation": null
}
Schema of the request body
{
"properties": {
"prompt": {
"type": "string",
"maxLength": 1000,
"minLength": 1,
"title": "Prompt To Generate Video",
"description": "A non-empty string up to 1000 characters describing what should appear in the output.",
"examples": [
"Children playing in the train"
]
},
"video_uri": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"format": "uri",
"title": "Video URI",
"description": "HTTPS URL pointing to a video or a data URI containing a video."
},
"reference_image_url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"format": "uri",
"title": "Reference Image URL",
"description": "HTTPS URL pointing to an image to use as style reference."
},
"aspect_ratio": {
"$ref": "#/components/schemas/VideoAspectRatio",
"title": "Aspect ratio",
"description": "The resolution of the output video.",
"default": "1280:720"
},
"seed": {
"anyOf": [
{
"type": "integer",
"maximum": 4294967295.0,
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Seed",
"description": "If unspecified, a random number is chosen. Varying the seed integer is a way to get different results."
},
"content_moderation": {
"anyOf": [
{
"$ref": "#/components/schemas/ContentModeration"
},
{
"type": "null"
}
],
"description": "Settings that affect the behavior of the content moderation system."
}
},
"type": "object",
"required": [
"prompt",
"video_uri",
"reference_image_url"
],
"title": "RunwayGenerateVideoFromVideoRequest",
"description": "Request model for Runway video to video generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Upload¶
POST /api/v1/firefly/upload¶
Upload
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Video Editing Generation¶
POST /api/v1/runway/video/editing-generation/video-upscale¶
Upscale Video
Description
Upscale a video using the RunwayML video up-scaling model. This endpoint accepts a video URL and enhances its quality/resolution using the RunwayML up-scaling service.
Args:
- request (RunwayVideoUpscaleRequest):
- video_url (HttpUrl): Video to upscale (<= 40s; each side < 4096px).
Returns: Json response with success status and the result containing the response, including task ID, status, and result URL (if available), or any error details.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"video_url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"format": "uri",
"title": "Video URL",
"description": "HTTPS URL pointing to a video or a data URI containing a video. The video must be less than 4096px on each side and duration may not exceed 40 seconds."
}
},
"type": "object",
"required": [
"video_url"
],
"title": "RunwayVideoUpscaleRequest",
"description": "Request model for Runway video upscaling."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Audio Generation¶
POST /api/v1/runway/audio/generation/text-to-speech¶
Text To Speech
Description
Generate speech from text.
Args:
- request (RunwayTextToSpeechRequest):
- prompt (str): Text to convert to speech.
- voice (RunwayVoice): Voice configuration (
type,preset_id). - model ("eleven_multilingual_v2"): TTS model.
Returns: Json response with success status and the result containing the response, including task ID, status, and result URL (if available), or any error details.
Input parameters
| Parameter | In | Type | Default | Nullable | Description |
|---|---|---|---|---|---|
APIKeyHeader |
header | string | N/A | No | API key |
Request body
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the request body
{
"properties": {
"prompt": {
"type": "string",
"maxLength": 1000,
"minLength": 1,
"title": "Text to Convert",
"description": "A non-empty string up to 1000 characters to convert to speech.",
"examples": [
"The quick brown fox jumps over the lazy dog"
]
},
"voice": {
"$ref": "#/components/schemas/RunwayVoice",
"title": "Voice Configuration",
"description": "The voice to use for the generated speech."
},
"model": {
"type": "string",
"const": "eleven_multilingual_v2",
"title": "Model",
"description": "The model variant to use. Currently only eleven_multilingual_v2 is supported.",
"default": "eleven_multilingual_v2"
}
},
"type": "object",
"required": [
"prompt",
"voice"
],
"title": "RunwayTextToSpeechRequest",
"description": "Request model for Runway text to speech generation."
}
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Response 422 Unprocessable Content
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Health¶
GET /health¶
Health Check
Description
Health check endpoint.
Response 200 OK
⚠️ This example has been generated automatically from the schema and it is not accurate. Refer to the schema for more information.
Schema of the response body
{
"type": "object",
"properties": {
"status": {
"type": "string",
"enum": [
"success"
]
},
"result": {
"oneOf": [
{
"type": "object"
},
{
"type": "array"
},
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
}
]
}
},
"required": [
"status",
"result"
],
"additionalProperties": false
}
Schemas¶
AlignmentModel¶
| Name | Type |
|---|---|
horizontal |
HorizontalAlignmentModel |
vertical |
VerticalAlignmentModel |
BackgroundAssetAdaptationRequest¶
| Name | Type |
|---|---|
audience |
string |
location |
string |
model_provider |
LlmProvider |
temperature |
number |
BackgroundCreationRequest¶
| Name | Type |
|---|---|
audience |
string |
location |
string |
model_provider |
LlmProvider |
temperature |
number |
Body_bria_enhance_prompt_api_v1_bria_prompt_enhance_prompt_post¶
| Name | Type |
|---|---|
prompt |
string |
Body_expand_image_async_api_v1_firefly_image_editing_generation_expand_image_post¶
| Name | Type |
|---|---|
image |
ImageReferenceModel |
mask |
MaskModel |
placement |
PlacementModel |
prompt |
|
seeds |
|
size |
SizeImagesAsyncModel |
Body_fill_image_async_api_v1_firefly_image_editing_generation_inpaint_post¶
| Name | Type |
|---|---|
image |
ImageReferenceModel |
mask |
MaskModel |
negative_prompt |
|
prompt |
|
prompt_biasing_locale_code |
|
seeds |
|
size |
SizeImagesAsyncModel |
Body_generate_images_async_api_v1_firefly_image_generation_generate_image_post¶
| Name | Type |
|---|---|
content_class |
ContentClass |
custom_model_id |
|
negative_prompt |
|
prompt |
string |
prompt_biasing_locale_code |
|
seeds |
|
size |
SizeImagesAsyncModel |
structure |
|
style |
|
upsampler_type |
string |
visual_intensity |
|
x_model_version |
CustomModel |
Body_generate_object_composite_async_api_v1_firefly_image_editing_generation_generate_product_background_post¶
| Name | Type |
|---|---|
content_class |
ContentClass |
image |
ImageReferenceModel |
mask |
ImageReferenceModel |
placement |
PlacementModel |
prompt |
string |
seeds |
|
size |
SizeImagesAsyncModel |
style |
Body_generate_similar_images_async_api_v1_firefly_image_generation_generate_variation_post¶
| Name | Type |
|---|---|
image |
ImageReferenceModel |
seeds |
|
x_model_version |
CustomModel |
Body_upload_api_v1_firefly_upload_post¶
| Name | Type |
|---|---|
file |
string(binary) |
BriaBlurBackgroundRequest¶
| Name | Type |
|---|---|
image |
|
preserve_alpha |
boolean |
scale |
integer |
sync |
boolean |
visual_input_content_moderation |
boolean |
visual_output_content_moderation |
boolean |
BriaCropForegroundRequest¶
| Name | Type |
|---|---|
force_background_detection |
boolean |
image |
|
padding |
integer |
preserve_alpha |
boolean |
sync |
boolean |
visual_input_content_moderation |
boolean |
visual_output_content_moderation |
boolean |
BriaEnhanceImageRequest¶
| Name | Type |
|---|---|
image |
|
preserve_alpha |
boolean |
resolution |
EnhanceResolution |
seed |
|
steps_num |
|
sync |
boolean |
visual_input_content_moderation |
boolean |
visual_output_content_moderation |
boolean |
BriaEraseForegroundRequest¶
| Name | Type |
|---|---|
image |
|
preserve_alpha |
boolean |
sync |
boolean |
visual_input_content_moderation |
boolean |
visual_output_content_moderation |
boolean |
BriaEraserRequest¶
| Name | Type |
|---|---|
image |
|
mask |
|
mask_type |
MaskType |
preserve_alpha |
boolean |
sync |
boolean |
visual_input_content_moderation |
boolean |
visual_output_content_moderation |
boolean |
BriaExpandImageRequest¶
| Name | Type |
|---|---|
aspect_ratio |
|
canvas_size |
|
image |
|
negative_prompt |
|
padding_bottom |
|
padding_left |
|
padding_right |
|
padding_top |
|
position |
|
preserve_alpha |
boolean |
prompt |
|
prompt_content_moderation |
boolean |
seed |
|
sync |
boolean |
visual_input_content_moderation |
boolean |
visual_output_content_moderation |
boolean |
BriaGenerateBackgroundRequest¶
| Name | Type |
|---|---|
enhance_ref_images |
boolean |
fast |
boolean |
force_background_detection |
boolean |
image |
|
negative_prompt |
|
original_quality |
boolean |
prompt |
|
prompt_content_moderation |
boolean |
ref_images |
|
refine_prompt |
boolean |
seed |
|
sync |
boolean |
visual_input_content_moderation |
boolean |
visual_output_content_moderation |
boolean |
BriaGenerateImageFastRequest¶
| Name | Type |
|---|---|
aspect_ratio |
string |
bria_model_version |
string |
content_moderation |
boolean |
enhance_image |
boolean |
guidance_method_1 |
|
guidance_method_1_image_file |
|
guidance_method_1_image_url |
|
guidance_method_1_scale |
|
guidance_method_2 |
|
guidance_method_2_image_file |
|
guidance_method_2_image_url |
|
guidance_method_2_scale |
|
image_prompt_file |
|
image_prompt_mode |
|
image_prompt_scale |
|
image_prompt_urls |
|
ip_signal |
boolean |
medium |
|
num_results |
integer |
prompt |
string |
prompt_content_moderation |
boolean |
prompt_enhancement |
boolean |
seed |
|
steps_num |
integer |
sync |
boolean |
BriaGenerateImageHDRequest¶
| Name | Type |
|---|---|
aspect_ratio |
string |
bria_model_version |
string |
content_moderation |
boolean |
enhance_image |
boolean |
ip_signal |
boolean |
medium |
|
negative_prompt |
|
num_results |
integer |
prompt |
string |
prompt_enhancement |
boolean |
seed |
|
steps_num |
integer |
sync |
boolean |
text_guidance_scale |
number |
BriaGenerateImageRequest¶
| Name | Type |
|---|---|
aspect_ratio |
string |
bria_model_version |
string |
content_moderation |
boolean |
enhance_image |
boolean |
guidance_method_1 |
|
guidance_method_1_image_file |
|
guidance_method_1_image_url |
|
guidance_method_1_scale |
|
guidance_method_2 |
|
guidance_method_2_image_file |
|
guidance_method_2_image_url |
|
guidance_method_2_scale |
|
image_prompt_file |
|
image_prompt_mode |
|
image_prompt_scale |
|
image_prompt_urls |
|
ip_signal |
boolean |
medium |
|
negative_prompt |
|
num_results |
integer |
prompt |
string |
prompt_content_moderation |
boolean |
prompt_enhancement |
boolean |
seed |
|
steps_num |
integer |
sync |
boolean |
text_guidance_scale |
number |
BriaGenerateProductBackgroundByImageRequest¶
| Name | Type |
|---|---|
aspect_ratio |
string |
canvas_for_packshot_size |
|
enhance_ref_image |
boolean |
force_rmbg |
boolean |
foreground_image_location |
|
foreground_image_size |
|
image_file |
|
image_url |
|
manual_placement_selection |
ManualPlacement |
num_results |
integer |
original_quality |
boolean |
padding_values |
Array<> |
placement_type |
PlacementType |
ref_image_file |
|
ref_image_influence |
number |
ref_image_urls |
|
sync |
boolean |
BriaGenerateProductBackgroundByTextRequest¶
| Name | Type |
|---|---|
aspect_ratio |
string |
canvas_for_packshot_size |
|
exclude_elements |
|
fast |
boolean |
force_rmbg |
boolean |
foreground_image_location |
|
foreground_image_size |
|
image_file |
|
image_url |
|
manual_placement_selection |
ManualPlacement |
num_results |
integer |
optimize_description |
boolean |
original_quality |
boolean |
padding_values |
Array<> |
placement_type |
PlacementType |
scene_description |
string |
sync |
boolean |
BriaGenerateProductShadowRequest¶
| Name | Type |
|---|---|
background_color |
|
force_rmbg |
boolean |
image_file |
|
image_url |
|
shadow_blur |
|
shadow_color |
|
shadow_height |
|
shadow_intensity |
|
shadow_offset |
|
shadow_type |
|
shadow_width |
BriaGenerateSolidBackgroundRequest¶
| Name | Type |
|---|---|
background_color |
string |
force_rmbg |
boolean |
image_file |
|
image_url |
BriaGenerateVariationRequest¶
| Name | Type |
|---|---|
content_moderation |
boolean |
enhance_image |
boolean |
fast |
boolean |
image_file |
|
image_url |
|
include_generation_prefix |
boolean |
ip_signal |
boolean |
num_results |
integer |
prompt |
string |
prompt_content_moderation |
boolean |
ref_image_influence |
number |
seed |
|
steps_num |
integer |
sync |
boolean |
tailored_model_id |
|
tailored_model_influence |
BriaGenerateVectorBaseRequest¶
| Name | Type |
|---|---|
aspect_ratio |
string |
bria_model_version |
string |
content_moderation |
boolean |
guidance_method_1 |
|
guidance_method_1_image_file |
|
guidance_method_1_image_url |
|
guidance_method_1_scale |
|
guidance_method_2 |
|
guidance_method_2_image_file |
|
guidance_method_2_image_url |
|
guidance_method_2_scale |
|
image_prompt_file |
|
image_prompt_mode |
|
image_prompt_scale |
|
image_prompt_urls |
|
ip_signal |
boolean |
negative_prompt |
|
num_results |
integer |
prompt |
string |
prompt_content_moderation |
boolean |
seed |
|
steps_num |
integer |
sync |
boolean |
text_guidance_scale |
number |
BriaGenerateVectorFastRequest¶
| Name | Type |
|---|---|
aspect_ratio |
string |
bria_model_version |
string |
content_moderation |
boolean |
guidance_method_1 |
|
guidance_method_1_image_file |
|
guidance_method_1_image_url |
|
guidance_method_1_scale |
|
guidance_method_2 |
|
guidance_method_2_image_file |
|
guidance_method_2_image_url |
|
guidance_method_2_scale |
|
image_prompt_file |
|
image_prompt_mode |
|
image_prompt_scale |
|
image_prompt_urls |
|
ip_signal |
boolean |
num_results |
integer |
prompt |
string |
prompt_content_moderation |
boolean |
seed |
|
steps_num |
integer |
sync |
boolean |
BriaGetMasksRequest¶
| Name | Type |
|---|---|
image_file |
|
image_url |
BriaInpaintingRequest¶
| Name | Type |
|---|---|
border_percentage |
|
image |
|
mask |
|
mask_type |
MaskType |
negative_prompt |
|
preserve_alpha |
boolean |
prompt |
string |
prompt_content_moderation |
boolean |
seed |
|
sync |
boolean |
visual_input_content_moderation |
boolean |
visual_output_content_moderation |
boolean |
BriaLoraCreateDatasetRequest¶
| Name | Type |
|---|---|
name |
string |
project_id |
integer |
BriaLoraCreateModelRequest¶
| Name | Type |
|---|---|
dataset_id |
integer |
description |
|
name |
string |
training_version |
string |
BriaLoraCreateProjectRequest¶
| Name | Type |
|---|---|
ip_description |
|
ip_medium |
string |
ip_name |
|
ip_type |
string |
project_description |
|
project_name |
string |
BriaLoraGenerateImagesRequest¶
| Name | Type |
|---|---|
aspect_ratio |
string |
fast |
boolean |
include_generation_prefix |
boolean |
model_id |
string |
model_influence |
|
num_results |
integer |
prompt |
string |
seed |
|
steps_num |
|
sync |
boolean |
BriaLoraGenerateVectorRequest¶
| Name | Type |
|---|---|
aspect_ratio |
string |
bria_model_version |
string |
content_moderation |
boolean |
guidance_method_1 |
|
guidance_method_1_image_file |
|
guidance_method_1_image_url |
|
guidance_method_1_scale |
|
guidance_method_2 |
|
guidance_method_2_image_file |
|
guidance_method_2_image_url |
|
guidance_method_2_scale |
|
image_prompt_file |
|
image_prompt_mode |
|
image_prompt_scale |
|
image_prompt_urls |
|
include_generation_prefix |
boolean |
model_id |
string |
model_influence |
|
negative_prompt |
|
num_results |
integer |
prompt |
string |
prompt_content_moderation |
boolean |
seed |
|
steps_num |
|
sync |
boolean |
text_guidance_scale |
BriaLoraUpdateDatasetRequest¶
| Name | Type |
|---|---|
caption_prefix |
|
dataset_id |
integer |
name |
|
status |
BriaLoraUpdateImageCaptionRequest¶
| Name | Type |
|---|---|
caption |
|
dataset_id |
integer |
image_id |
integer |
regenerate_caption |
boolean |
BriaLoraUpdateModelRequest¶
| Name | Type |
|---|---|
description |
|
model_id |
integer |
name |
BriaLoraUpdateProjectRequest¶
| Name | Type |
|---|---|
ip_description |
|
ip_name |
|
project_description |
|
project_id |
integer |
project_name |
BriaLoraUploadImageRequest¶
| Name | Type |
|---|---|
dataset_id |
integer |
file_path |
|
image_name |
|
image_url |
BriaProductCutoutRequest¶
| Name | Type |
|---|---|
force_rmbg |
boolean |
image_file |
|
image_url |
BriaRemoveBackgroundRequest¶
| Name | Type |
|---|---|
image |
|
preserve_alpha |
boolean |
sync |
boolean |
visual_input_content_moderation |
boolean |
visual_output_content_moderation |
boolean |
BriaStatusResponse¶
| Name | Type |
|---|---|
error |
|
request_id |
string |
result |
|
status |
string |
BriaUpscaleImageRequest¶
| Name | Type |
|---|---|
desired_increase |
integer |
image |
|
preserve_alpha |
boolean |
sync |
boolean |
visual_input_content_moderation |
boolean |
visual_output_content_moderation |
boolean |
BriaVideoRemoveBackgroundRequest¶
| Name | Type |
|---|---|
background_color |
|
output_container_and_codec |
|
video |
string(uri) |
CharacterInput¶
| Name | Type |
|---|---|
type |
string |
uri |
string(uri) |
ContentClass¶
Type: string
ContentModeration¶
| Name | Type |
|---|---|
public_figure_threshold |
string |
ControlnetType¶
Type: string
ControlReferenceType¶
Type: string
CustomModel¶
Type: string
EnhanceResolution¶
Type: string
GeminiEditImageRequest¶
| Name | Type |
|---|---|
edit_prompt |
|
edit_steps |
|
image_url |
string(uri) |
safety_category |
|
safety_method |
|
safety_threshold |
GeminiGenerateImageRequest¶
| Name | Type |
|---|---|
image_urls |
|
prompt |
string |
safety_category |
|
safety_method |
|
safety_threshold |
GeminiGenerateImageSequenceRequest¶
| Name | Type |
|---|---|
prompt |
string |
safety_category |
|
safety_method |
|
safety_threshold |
google__genai__types__PersonGeneration¶
Type: string
GPTEditImageRequest¶
| Name | Type |
|---|---|
aspect_ratio |
string |
image_url |
string(uri) |
number_of_images |
integer |
prompt |
string |
GPTGenerateImageRequest¶
| Name | Type |
|---|---|
aspect_ratio |
string |
background |
GPTImageBackground |
number_of_images |
integer |
prompt |
string |
quality |
GPTImageQuality |
GPTImageBackground¶
Type: string
GPTImageQuality¶
Type: string
GPTInpaintingRequest¶
| Name | Type |
|---|---|
border_percentage |
number |
image_file |
|
image_url |
|
inpaint_border_only |
boolean |
mask_file |
|
mask_url |
|
prompt |
string |
HarmBlockMethod¶
Type: string
HarmBlockThreshold¶
Type: string
HarmCategory¶
Type: string
HorizontalAlignmentModel¶
Type: string
HTTPValidationError¶
| Name | Type |
|---|---|
detail |
Array<ValidationError> |
ImageAspectRatio¶
Type: string
ImageCaptionMode¶
Type: string
ImageCaptionRequest¶
| Name | Type |
|---|---|
image_url |
string(uri) |
mode |
ImageCaptionMode |
model_provider |
LlmProvider |
nbr_tags |
integer |
possible_tags |
ImageCreationRequest¶
| Name | Type |
|---|---|
audience |
string |
location |
string |
model_provider |
LlmProvider |
temperature |
number |
ImagenBackgroundRequest¶
| Name | Type |
|---|---|
image_url |
string(uri) |
number_of_images |
integer |
person_generation |
google__genai__types__PersonGeneration |
prompt |
string |
safety_filter_level |
SafetyFilterLevel |
seed |
ImagenExpandImageRequest¶
| Name | Type |
|---|---|
image_url |
string(uri) |
mask_dilation |
number |
number_of_images |
integer |
padding_bottom |
|
padding_left |
|
padding_right |
|
padding_top |
|
person_generation |
google__genai__types__PersonGeneration |
position |
|
prompt |
string |
safety_filter_level |
SafetyFilterLevel |
target_height |
integer |
target_width |
integer |
ImagenGenerateImageRequest¶
| Name | Type |
|---|---|
add_watermark |
boolean |
aspect_ratio |
string |
model_name |
|
number_of_images |
integer |
person_generation |
google__genai__types__PersonGeneration |
prompt |
string |
safety_filter_level |
SafetyFilterLevel |
use_fast_model |
boolean |
ImagenImageGuidanceRequest¶
| Name | Type |
|---|---|
aspect_ratio |
|
guidance_type |
string |
person_generation |
google__genai__types__PersonGeneration |
prompt |
|
ref_image_1_description |
|
ref_image_1_url |
string(uri) |
ref_image_2_description |
|
ref_image_2_url |
|
safety_filter_level |
SafetyFilterLevel |
subject_type |
ImagenInpaintingRequest¶
| Name | Type |
|---|---|
image_url |
string(uri) |
mask_dilation |
|
mask_mode |
|
operation_type |
string |
person_generation |
google__genai__types__PersonGeneration |
prompt |
|
removal_mode |
|
safety_filter_level |
SafetyFilterLevel |
segmentation_classes |
ImagenVariationRequest¶
| Name | Type |
|---|---|
aspect_ratio |
|
control_type |
ControlReferenceType |
image_url |
string(uri) |
number_of_images |
integer |
person_generation |
google__genai__types__PersonGeneration |
prompt |
|
safety_filter_level |
SafetyFilterLevel |
ImagePromptMode¶
Type: string
ImageReferenceModel¶
| Name | Type |
|---|---|
source |
SourceModel |
InsertModel¶
| Name | Type |
|---|---|
bottom |
integer |
center |
integer |
left |
integer |
right |
integer |
top |
integer |
LlmProvider¶
Type: string
ManualPlacement¶
Type: string
MaskModel¶
| Name | Type |
|---|---|
invert |
boolean |
source |
SourceModel |
MaskReferenceMode¶
Type: string
MaskType¶
Type: string
ModelName¶
Type: string
PlacementModel¶
| Name | Type |
|---|---|
alignment |
AlignmentModel |
insert |
InsertModel |
PlacementType¶
Type: string
PromptEnhancementRequest¶
| Name | Type |
|---|---|
model_provider |
LlmProvider |
prompt |
string |
temperature |
number |
ReferenceImage¶
| Name | Type |
|---|---|
tag |
|
uri |
RemovalMode¶
Type: string
RunwayGenerateImageRequest¶
| Name | Type |
|---|---|
aspect_ratio |
ImageAspectRatio |
content_moderation |
|
model |
string |
prompt |
string |
reference_images_url |
|
seed |
RunwayGenerateVideoFromImageRequest¶
| Name | Type |
|---|---|
aspect_ratio |
VideoAspectRatio |
content_moderation |
|
duration |
integer |
image_url |
|
model |
string |
prompt |
string |
seed |
RunwayGenerateVideoFromMotionRequest¶
| Name | Type |
|---|---|
aspect_ratio |
VideoAspectRatio |
body_control |
boolean |
character |
CharacterInput |
content_moderation |
|
expression_intensity |
integer |
reference_url |
string(uri) |
seed |
RunwayGenerateVideoFromTextRequest¶
| Name | Type |
|---|---|
aspect_ratio |
string |
duration |
integer |
model |
string |
prompt |
string |
seed |
RunwayGenerateVideoFromVideoRequest¶
| Name | Type |
|---|---|
aspect_ratio |
VideoAspectRatio |
content_moderation |
|
prompt |
string |
reference_image_url |
string(uri) |
seed |
|
video_uri |
string(uri) |
RunwayTextToSpeechRequest¶
| Name | Type |
|---|---|
model |
string |
prompt |
string |
voice |
RunwayVoice |
RunwayVideoUpscaleRequest¶
| Name | Type |
|---|---|
video_url |
string(uri) |
RunwayVoice¶
| Name | Type |
|---|---|
preset_id |
string |
type |
string |
SafetyFilterLevel¶
Type: string
SizeImagesAsyncModel¶
| Name | Type |
|---|---|
height |
integer |
width |
integer |
SourceModel¶
| Name | Type |
|---|---|
upload_id |
|
url |
src__models__veo__PersonGeneration¶
Type: string
StructureModel¶
| Name | Type |
|---|---|
image_reference |
ImageReferenceModel |
strength |
integer |
StyleModel¶
| Name | Type |
|---|---|
image_reference |
ImageReferenceModel |
presets |
Array<string> |
strength |
integer |
SubjectEnhancementRequest¶
| Name | Type |
|---|---|
audience |
string |
location |
string |
model_provider |
LlmProvider |
subject |
string |
temperature |
number |
SubjectPosePromptRequest¶
| Name | Type |
|---|---|
model_provider |
LlmProvider |
subject |
string |
temperature |
number |
SubjectReferenceType¶
Type: string
ValidationError¶
| Name | Type |
|---|---|
loc |
Array<> |
msg |
string |
type |
string |
VeoDuration¶
Type: integer
VeoGenerateVideoRequest¶
| Name | Type |
|---|---|
aspect_ratio |
string |
duration |
VeoDuration |
enhance_prompt |
|
model |
VeoModel |
negative_prompt |
|
person_generation |
|
prompt |
string |
seed |
|
start_image_url |
VeoModel¶
Type: string
VerticalAlignmentModel¶
Type: string
VideoAspectRatio¶
Type: string
VideoCaptionMode¶
Type: string
VideoCaptionRequest¶
| Name | Type |
|---|---|
mode |
VideoCaptionMode |
nbr_tags |
integer |
video_url |
string(uri) |
Security schemes¶
| Name | Type | Scheme | Description |
|---|---|---|---|
| APIKeyHeader | apiKey |
Tags¶
| Name | Description |
|---|---|
| Health | Health check endpoints |
| Status | Status check endpoints |
| Upload | Upload endpoints |
| Prompt Enhancement | Prompt generation and enhancement services |
| Media Captioning | Image and video captioning services |
| Image Editing | Basic image editing operations |
| Image Generation | Image generation services |
| Image Editing Generation | Advanced image editing with AI generation |
| Video Editing | Basic video editing operations |
| Video Generation | Video generation services |
| Video Editing Generation | Advanced video editing with AI generation |
| LoRA Project Management | LoRA project management services |
| LoRA Training | LoRA training services |
| Audio Generation | Audio generation services |
Health¶
- Lightweight probe for service uptime.
- Endpoints:
GET /health. - See OpenAPI tag: Health in the reference above.
Status¶
- Check async job state and cancel running jobs across providers.
- Endpoints:
- Firefly:
GET /api/v1/firefly/status/{task_id},DELETE /api/v1/firefly/cancel/{task_id} - Runway:
GET /api/v1/runway/status/{task_id},DELETE /api/v1/runway/cancel/{task_id} - BRIA:
GET /api/v1/bria/status/{task_id} - See OpenAPI tag: Status.
Upload¶
- Provider upload helpers (e.g., Firefly image upload).
- Endpoints:
POST /api/v1/firefly/upload(multipart). - See OpenAPI tag: Upload.
Prompt Enhancement¶
- Generate or adapt prompts (background, subject, pose) for better generations.
- Endpoints:
/api/v1/prompt/*, andPOST /api/v1/bria/prompt/enhance-prompt. - See OpenAPI tag: Prompt Enhancement.
Media Captioning¶
- Create captions/tags for images and videos.
- Endpoints:
POST /api/v1/caption/image,POST /api/v1/caption/video. - See OpenAPI tag: Media Captioning.
Image Editing¶
- Deterministic edits like background removal, cutout, cropping, masks.
- Representative endpoints (BRIA):
POST /api/v1/bria/image/editing/remove-backgroundPOST /api/v1/bria/image/editing/product-cutoutPOST /api/v1/bria/image/editing/crop-foregroundPOST /api/v1/bria/image/editing/get-masks- See OpenAPI tag: Image Editing.
Image Generation¶
- Text-to-image and guided image generations across providers.
- Representative endpoints:
- BRIA:
POST /api/v1/bria/image/generation/* - Firefly:
POST /api/v1/firefly/image/generation/* - Google Vision (Imagen/Gemini):
POST /api/v1/google-vision/image/generation/* - OpenAI (GPT Image):
POST /api/v1/openai/image/generation/generate-image - Bria LoRA:
POST /api/v1/bria-lora/image/generation/* - See OpenAPI tag: Image Generation.
Image Editing Generation¶
- Generative edits (inpaint/fill/expand/enhance/background synthesis).
- Representative endpoints:
- BRIA:
POST /api/v1/bria/image/editing-generation/* - Firefly:
POST /api/v1/firefly/image/editing-generation/* - Google Vision (Imagen/Gemini):
POST /api/v1/google-vision/image/editing-generation/* - OpenAI (GPT Image):
POST /api/v1/openai/image/editing-generation/* - See OpenAPI tag: Image Editing Generation.
Video Editing¶
- Deterministic video edits (e.g., background removal).
- Representative endpoints:
- BRIA:
POST /api/v1/bria/video/editing/remove-background(alias also available) - See OpenAPI tag: Video Editing.
Video Generation¶
- Text/image/video-to-video generation.
- Representative endpoints:
- Runway:
POST /api/v1/runway/video/generation/* - Google Vision (VEO):
POST /api/v1/google-vision/video/generation/generate-video - See OpenAPI tag: Video Generation.
Video Editing Generation¶
- Generative video operations (e.g., upscaling/enhancement).
- Endpoints:
POST /api/v1/runway/video/editing-generation/video-upscale. - See OpenAPI tag: Video Editing Generation.
Audio Generation¶
- Text-to-speech.
- Endpoints:
POST /api/v1/runway/audio/generation/text-to-speech. - See OpenAPI tag: Audio Generation.
LoRA Project Management¶
- Manage LoRA projects, datasets, and models.
- Representative endpoints:
/api/v1/bria-lora/projects,/api/v1/bria-lora/datasets,/api/v1/bria-lora/models(+ resource subpaths). - See OpenAPI tag: LoRA Project Management.
LoRA Training¶
- Start/stop LoRA model training.
- Endpoints:
POST /api/v1/bria-lora/models/{model_id}/training/{start|stop}. - See OpenAPI tag: LoRA Training.