fal Sandbox is here - run all your models together! 🏖️
DocsBlogPricingEnterpriseCareersResearch Grants
Log-inSign-up

Fibo JSON to Image

bria/fibo/generate
SOTA Open source model trained on licensed data, transforming intent into structured control for precise, high-quality AI image generation in enterprise and agentic workflows.
Inference
Commercial use
Partner
Schema
LLMs
PlaygroundAPIExamples

Input

Drag & drop an image, paste from clipboard, or click the image area to upload

Structured Prompt will be populated from your instructions or uploaded assets, giving you predictable, repeatable control without any guesswork.

Additional Settings

Customize your input with more control.

Result

Idle

Waiting for your input...

Your request will cost $0.04 per image.

Logs

🌍 Why FIBO?

Text-to-image models have mastered imagination - but not control. FIBO changes that. FIBO is trained on structured JSON captions up to 1,000+ words and designed to understand and control different visual parameters such as lighting, composition, color, and camera settings, enabling precise and reproducible outputs. With only 8 billion parameters, FIBO provides a new level of image quality, prompt adherence and professional control. Enterprises demand repeatability, governance, and transparency. FIBO delivers - open-source, rights-clear, and ready for production.

🔑 Key Features

  • LLM guided JSON-native prompting: structured schemas up to 1,000+ words (lighting, camera, composition, DoF)
  • Iterative controlled generation: generate images from short prompts or keep refining and get inspiration from detailed JSONs and input images
  • Disentangled control: tweak a single attribute (e.g., camera angle) without breaking the scene.
  • Enterprise-grade: 100% licensed data; governance, repeatability, and legal clarity.
  • Strong prompt adherence: high alignment on PRISM-style evaluations.

Benchmark:

benchmark

đź’ˇ What can you do with FIBO?

Generate

Start with a quick idea. FIBO’s language model expands your short prompt into a rich, structured JSON prompt, then generates the image. You get both the image and the expanded prompt.

Refine

Continue from a detailed structured prompt and add a small instruction - for example, “backlit,” “85 mm,” or “warmer skin tones.” FIBO updates only the requested attributes, re-generates the image, and returns the refined prompt alongside it.

Inspire

Provide an image instead of text. FIBO’s vision-language model extracts a detailed prompt describing it, combines that with your creative intent, and generates new, related images - ideal for exploring new directions without altering the original.