Skip to content

Overview

Bria’s Image Generation API provides builders with a flexible and controllable way to generate high-quality visuals from textual prompts or reference images. It supports various resolutions, aspect ratios, and generation speeds, enabling scalable and efficient production of photos, illustrations, and vector graphics for commercial use.

description: | V2 Endpoints (Recommended): Our latest image generation API (V2) is built around FIBO, a next-gen visual model trained on structured JSON descriptions of images for precise, controllable generation. These endpoints utilize a two-step process:

  1. A VLM Bridge translates your input (text/images) into a detailed, machine-readable structured_prompt (JSON).
  2. The FIBO image model generates the final image based on the structured_prompt.

This API offers two VLM bridge options:

  • Gemini 2.5 Flash: Used by the /image/generate endpoints for state-of-the-art, detailed prompt creation.
  • FIBO-VLM (Open): (Coming Soon) Used by the /image/generate/open endpoints. This is Bria's open-source VLM bridge, which supports flexible on-prem deployment.

You can use the all-in-one /image/generate endpoints or decouple these steps using the /structured_prompt/generate endpoints for maximum control and automation. See the v2 endpoints tag description below for more details.

V1 Endpoints: We also provide access to our previous generation (V1) endpoints. These offer distinct pipelines like Base, Fast, HD, Vector generation, and Reimagine. Some V1 endpoints support unique Guidance Methods like ControlNets. See the v1 endpoints tag description below for details on these legacy features.

IP-related prompts Our models are trained exclusively on fully licensed, safe-for-commercial-use data. Prompts that reference public figures, brands, or other protected content may result in generic or altered outputs. These prompts are not blocked, but results may differ from what you expect. If an IP-related signal is detected in the prompt, the following warning will appear in the API response:

  This prompt may contain intellectual property (IP)-protected content. 
  To ensure compliance and safety, certain elements may be omitted or altered. 
  As a result, the output may not fully meet your request.

Advanced Customization and Access: As part of Bria’s Source Code & Weights product, developers seeking deeper customization can access Bria’s source-available GenAI models via Hugging Face. This allows full control over fine-tuning, pipeline creation, and integration into proprietary workflows—empowering AI teams to develop and optimize their own generative AI solutions.

Register and get API Access
Download OpenAPI description
image-generation.json
image-generation.yaml
Languages
Servers

https://engine.prod.bria-api.com/v2/

https://engine.prod.bria-api.com/v1/

v2 endpoints

Our latest image generation API (V2) is built around FIBO, a next-gen visual model trained on structured JSON descriptions of images for precise, controllable generation.

Key Features:

  • Structured Control: Generate images based on detailed JSON prompts for deterministic and auditable results.
  • VLM Bridge Options: Choose your intent translation engine:
    • Gemini 2.5 Flash (Default): Uses Gemini 2.5 Flash for state-of-the-art understanding. (/image/generate, /structured_prompt/generate)
    • FIBO-VLM (Open): (Coming Soon) Uses Bria's FIBO-VLM (open-source model) for efficient translation and flexible on-prem deployment. (/image/generate/open, /structured_prompt/generate/open)
  • Decoupled Workflow: Optionally generate the structured_prompt first (e.g., /structured_prompt/generate) for inspection, editing, automation, or hybrid deployments before generating the image (e.g., /image/generate).

Asynchronous Requests and the Status Service

Bria API v2 endpoints process requests asynchronously by default. When you make an asynchronous request, the API immediately returns a request_id and a status_url instead of the final result. Use the Status Service to track the request's progress until it reaches a completed state.

See the full guide at Status Service Documentation for complete details and usage examples.

Operations

v1 endpoints

Endpoints that are part of BRIA API version 1. These endpoints offer various pipelines but lack the structured prompt control of V2.

V1 Pipelines Include:

  • /text-to-image/base: Standard image generation.
  • /text-to-image/fast: Speed-optimized image generation.
  • /text-to-image/hd: High-resolution image generation.
  • /text-to-vector/base & /fast: Vector graphic generation (Beta).
  • /reimagine: Structure-preserving image generation.
  • /prompt_enhancer: Utility to enhance simple prompts.
Operations