briaai / Fibo-Edit-Dev

Fibo Edit is the new edition to the Fibo Family - a set of models that follow the VGL (Visual GenAI Language) Paradigm.
This 8B parameter image-to-image diffusion model is designed for precise, deterministic, and controllable editing.

🌍 What's Fibo Edit?

Unlike traditional edit models that rely on loose text prompts, Fibo Edit introduces a new paradigm of structured control. It operates on Structured JSON inputs paired with a source image and a mask, enabling explicit, interpretable, and repeatable editing workflows optimized for professional production environments.

Developed by Bria AI, Fibo Edit prioritizes transparency, legal safety, and granular control, ranking among the top 3 editing models in open benchmarks for its aesthetic quality and adherence.

News

• 2026-1-16: Fibo Edit released on Hugging Face 🎉
• 2026-1-16: Integrated with Diffusers library 🧨

🔑 Key Features

• Structured JSON Control : Move beyond "prompt drift." Define edits with explicit parameters (lighting, composition, style) using a structured JSON format for deterministic results.
• Native Masking : Built-in support for mask-based editing allows you to target specific regions of an image with pixel-perfect precision, leaving the rest untouched.
• Production-Ready Architecture : At 8B parameters, the model balances high-fidelity output with the speed and efficiency required for commercial pipelines.
• Deep Customization : The lightweight architecture empowers researchers to build specialized "Edit" models for domain-specific tasks without compromising quality.
• Responsible & Licensed : Trained exclusively on fully licensed data, ensuring zero copyright infringement risks for commercial users.

⚡ Quick Start

🚀 Try Fibo Edit now →

Fibo Edit is available everywhere you build, either as source-code and weights, ComfyUI nodes or API endpoints.

API Endpoint:

• Bria.ai
• Fal.ai
• Replicate
• Bria Fibo Lab

Source-Code & Weights

• The model is open source for non-commercial use with this license .
• For commercial use Click here .

Quick Start Guide

clone the repository and install the requirements

git clone https://github.com/briaai/Fibo-Edit.git
cd Fibo-Edit

install the requirements

pip install git+https://github.com/huggingface/diffusers torch torchvision openai boltons ujson sentencepiece accelerate transformers

Promptify Setup

The edit_promptify module uses a VLM to analyze images and generate structured JSON prompts. By default, it uses OpenRouter to access the underlying VLM.

Option 1: OpenRouter API (Recommended)

1. Create an account at openrouter.ai
2. Generate an API key from your dashboard
3. Set the API key as an environment variable:

   export OPENROUTER_API_KEY=your_openrouter_api_key

Option 2: Use Your Own LLM (Advanced)

For advanced users who prefer to use a different LLM provider, you can use the schemas and system prompts directly with any compatible model. The structured prompt schemas and system prompts are available in the src/ directory and can be adapted for use with OpenAI, Anthropic, local models, or any other LLM of your choice.

Image + Mask

import torch
from diffusers import DiffusionPipeline
from PIL import Image
import json

# 1. Load the pipeline
pipe = DiffusionPipeline.from_pretrained(
    "briaai/Fibo-Edit",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True
)
pipe.to("cuda")

# 2. Load your source image and mask
source_image = Image.open("path/to/image.png")
mask_image = Image.open("path/to/mask.png")

# 3. Define the structured edit request
# Unlike standard prompts, this JSON explicitly targets the attributes to change.
edit_instruction = {
    "edit_type": "material_change",
    "target_object": "couch",
    "new_attribute": "red velvet texture",
    "lighting": "soft studio light"
}

# 4. Run the edit
result = pipe(
    image=source_image,
    mask_image=mask_image,
    prompt=json.dumps(edit_instruction), # Passing the structured JSON as the prompt
    num_inference_steps=30
).images[0]

result.save("fibo_edit_result.png")

Only Image

import torch
from diffusers import DiffusionPipeline
from PIL import Image
import json

# 1. Load the pipeline
pipe = DiffusionPipeline.from_pretrained(
    "briaai/Fibo-Edit",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True
)
pipe.to("cuda")

# 2. Load your source image and mask
source_image = Image.open("path/to/image.png")

# 3. Define the structured edit request
# Unlike standard prompts, this JSON explicitly targets the attributes to change.
edit_instruction = {
    "edit_type": "material_change",
    "target_object": "couch",
    "new_attribute": "red velvet texture",
    "lighting": "soft studio light"
}

# 4. Run the edit
result = pipe(
    image=source_image,
    mask_image=mask_image,
    prompt=json.dumps(edit_instruction), # Passing the structured JSON as the prompt
    num_inference_steps=30
).images[0]

result.save("fibo_edit_result.png")

More Examples

Advanced Usage

Gemini Setup [optional]

FIBO supports any VLM as part of the pipeline. To use Gemini as VLM backbone for FIBO, follow these instructions:

1. Obtain a Gemini API Key
   Sign up for the Google AI Studio (Gemini) and create an API key.

2. Set the API Key as an Environment Variable
   Store your Gemini API key in the GEMINI_API_KEY environment variable:

   export GEMINI_API_KEY=your_gemini_api_key
   

   You can add the above line to your .bashrc , .zshrc , or similar shell profile for persistence.

see the examples in the examples directory for more details.

🧠 Training and Architecture

Fibo Edit is an 8B-parameter DiT-based, flow-matching text-to-image model trained exclusively on licensed data and on > long, structured JSON captions (~1,000 words each), enabling strong prompt adherence and professional-grade control. It uses SmolLM3-3B as the text encoder with a novel DimFusion conditioning architecture for efficient long-caption training, and Wan 2.2 as the VAE. The structured supervision promotes native disentanglement for targeted, iterative refinement without prompt drift, while VLM-assisted prompting expands short user intents, fills in missing details, and extracts/edits structured prompts from images using our fine-tuned Qwen-2.5 -based VLM or Gemini 2.5 Flash . For reproducibility, we provide the assistant system prompt and the structured-prompt JSON schema across the “Generate,” “Refine,” and “Inspire” modes.

More Samples

If you have questions about this repository, feedback to share, or want to contribute directly, we welcome your issues and pull requests on GitHub. Your contributions help make FIBO better for everyone.

If you're passionate about fundamental research, we're hiring full-time employees (FTEs) and research interns. Don't wait - reach out to us at [email protected]

Citation

We kindly encourage citation of our work if you find it useful.

@article{gutflaish2025generating,
  title={Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions},
  author={Gutflaish, Eyal and Kachlon, Eliran and Zisman, Hezi and Hacham, Tal and Sarid, Nimrod and Visheratin, Alexander and Huberman, Saar and Davidi, Gal and Bukchin, Guy and Goldberg, Kfir and others},
  journal={arXiv preprint arXiv:2511.06876},
  year={2025}
}

❤️ FIBO model card and ⭐ Star FIBO on GitHub to join the movement for responsible generative AI!