Routes for generating images and structured prompts using the FIBO architecture.
Overview
Bria’s Image Generation API provides builders with a flexible and controllable way to generate high-quality photos and illustrations from textual prompts or reference images. It supports various resolutions, aspect ratios, and generation speeds, enabling scalable and efficient production for commercial use.
API Access
You can register and access the API Token through Bria's platform by clicking here.
Core Technology: The FIBO Architecture
Our API is built around FIBO, a next-gen visual model trained on structured JSON descriptions. This ensures precise, controllable generation through a unique two-step process:
- Translation: A VLM Bridge converts your input (text/images) into a detailed
structured_prompt(JSON). - Generation: The FIBO image model generates the final visual based on that deterministic JSON instruction.
Choose Your Pipeline
Select the pipeline that best fits your performance and privacy needs:
- Standard Pipeline (Recommended): Best for maximum nuance, instruction adherence, and visual fidelity. Utilizes the Gemini 2.5 Flash Bridge and the full FIBO Model.
- Fibo Lite Pipeline (Speed & Privacy): Best for rapid inference and environments requiring data sovereignty. Utilizes the open-source FIBO-VLM Bridge and Fibo Lite Model. Both components are optimized for speed, and this combination enables fully local, on-prem deployment. To learn more, contact us at support@bria.ai.
IP-Related Prompts
Our models are trained exclusively on fully licensed, safe-for-commercial-use data. Prompts referencing public figures or protected brands may result in generic outputs. If an IP signal is detected, a warning will be included in the API response.
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.
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.
Download OpenAPI description
Languages
Servers
https://engine.prod.bria-api.com/v2/