Bria-AI/FIBO

FIBO is a SOTA, first open-source, JSON-native text-to-image model built for controllable, predictable, and legally safe image generation.

39
/ 100
Emerging

Built on an 8B-parameter diffusion architecture trained exclusively on structured JSON captions (1,000+ words), FIBO achieves native attribute disentanglement—modifying lighting, camera, or composition without prompt drift. The model integrates Vision-Language Models (VLM-guided prompting) to transform short prompts into detailed schemas, and supports iterative refinement workflows across ComfyUI nodes, Hugging Face, and commercial APIs (Bria, Fal.ai, Replicate).

305 stars.

No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 10 / 25

How are scores calculated?

Stars

305

Forks

15

Language

Python

License

Last pushed

Jan 07, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/Bria-AI/FIBO"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.