Update README.md

README.md

@@ -1,242 +1,111 @@
 ---
+license: cc-by-nc-4.0
 language:
 - en
 base_model:
 - briaai/FIBO
-pipeline_tag: text-to-image
 library_name: diffusers
-license: cc-by-nc-4.0
-license_name: bria-fibo
-license_link: https://creativecommons.org/licenses/by-nc/4.0/deed.en
 tags:
-- lora
-- guidance-distillation
-- text-to-image
-- fast-inference
-- bria
-- fibo
-extra_gated_heading: Access FIBO Guidance Distillation LoRA
-extra_gated_description: >-
-  This model is an extension of Bria AI's FIBO model. Weights are open source for non-commercial use only, per the
-  provided [license](https://creativecommons.org/licenses/by-nc/4.0/deed.en).
-extra_gated_fields:
-  Name: text
-  Email: text
-  Company/Org name: text
-  Company Website URL: text
-  Discord user: text
-  I agree to BRIA’s Privacy policy, Terms & conditions, and acknowledge Non commercial use to be Personal use / Academy / Non profit (direct or indirect): checkbox
+- MLX
 ---
-
-<!-- ===================== HEADER ===================== -->
 <p align="center">
   <img src="https://bria-public.s3.us-east-1.amazonaws.com/Bria-logo.svg" width="200"/>
 </p>
-
-<div align="center">
-
-# FIBO Guidance Distillation LoRA ⚡
-
-[![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-blue)](https://huggingface.co/briaai/FIBO)
-[![GitHub](https://img.shields.io/badge/GitHub-Repo-181717?logo=github)](https://github.com/Bria-AI/FIBO)
-[![License](https://img.shields.io/badge/License-CC%20BY--NC%204.0-lightgrey)](https://creativecommons.org/licenses/by-nc/4.0/deed.en)
-
-</div>
-
 <p align="center">
-  <img src="assets/shuttle.png" alt="FIBO Lite Hero" width="100%"/>
-</p>
+  <!-- GitHub Repo -->
+  <a href="https://github.com/Bria-AI/FIBO" target="_blank">
+    <img
+      alt="GitHub Repo"
+      src="https://img.shields.io/badge/GitHub-Repo-181717?logo=github&logoColor=white&style=for-the-badge"
+    />
+  </a>
+  &nbsp;
+
+  <!-- Hugging Face Demo -->
+  <a href="https://huggingface.co/spaces/briaai/FIBO" target="_blank">
+    <img
+      alt="Hugging Face Demo"
+      src="https://img.shields.io/badge/Hugging%20Face-Demo-FFD21E?logo=huggingface&logoColor=black&style=for-the-badge"
+    />
+  </a>
+  &nbsp;
+
+  <!-- FIBO Demo on Bria (replace URL if you have a specific demo link) -->
+  <a href="https://platform.bria.ai/labs/fibo" target="_blank">
+    <img
+      alt="FIBO Demo on Bria"
+      src="https://img.shields.io/badge/FIBO%20Demo-Bria-6C47FF?style=for-the-badge"
+    />
+  </a>
+  &nbsp;
+
+  <!-- Bria Platform -->
+  <a href="https://platform.bria.ai" target="_blank">
+    <img
+      alt="Bria Platform"
+      src="https://img.shields.io/badge/Bria-Platform-0EA5E9?style=for-the-badge"
+    />
+  </a>
+  &nbsp;
+
+  <!-- Bria Discord -->
+  <a href="https://discord.com/invite/Nxe9YW9zHS" target="_blank">
+    <img
+      alt="Bria Discord"
+      src="https://img.shields.io/badge/Discord-Join-5865F2?logo=discord&logoColor=white&style=for-the-badge"
+    />
+  </a>
+  &nbsp;
+
+  <!-- Tech Paper -->
+  <a href="https://arxiv.org/abs/2511.06876" target="_blank">
+    <img
+      alt="Tech Paper"
+      src="https://img.shields.io/badge/Tech%20Paper-lightgrey?logo=arxiv&logoColor=red&style=for-the-badge"
+    />
+  </a>
+  &nbsp;
+
+  <!-- Mflux -->
+  <a href="https://github.com/filipstrand/mflux" target="_blank">
+    <img
+      alt="Mflux"
+      src="https://img.shields.io/badge/Mflux-Repo-blue?logo=github&logoColor=white&style=for-the-badge"
+    />
+  </a>
+  &nbsp;
 
-<p align="center">
-  <b>Accelerate FIBO inference by 2x with a distillation LoRA.</b>
-  <br>
-  <i>This LoRA distills classifier-free guidance into the model, allowing you to generate images with 2x faster inference. As with most distillation approaches, there may be a slight degradation in quality compared to the full model.</i>
 </p>
-
----
-
-## 🚀 Overview
-
-This is a **Guidance Distillation LoRA** for the [**FIBO**](https://huggingface.co/briaai/FIBO) text-to-image model. 
-
-By distilling the knowledge of the teacher model (typically running at high guidance scales) into this lightweight adapter, you can run inference with **Guidance Scale (CFG) = 1.0**. This skips the negative prompt pass entirely, effectively **doubling the inference speed** compared to standard generation. As this is a distillation LoRA, there is a slight quality degradation compared to the full model at CFG=5, though the speed benefits often outweigh this tradeoff for many use cases.
-
-### ✨ What's New
-
-- **Nov 2025**: Initial release of FIBO Guidance Distillation LoRA
-- 2x inference speedup with maintained quality
-- Compatible with standard diffusers pipeline
-
-### 🔑 Key Benefits
-
-*   **2x Faster Inference**: Running at `guidance_scale=1` means calculating the noise prediction only once per step instead of twice.
-*   **Quality Tradeoff**: As a distillation LoRA, there is a slight quality degradation compared to the full model at CFG=5, but the speed gains make it ideal for rapid iteration and production workflows where speed is prioritized.
-*   **Drop-in Replacement**: Works seamlessly with existing FIBO workflows—just  set `guidance_scale=1.0`.
-*   **Memory Efficient**: Minimal additional GPU memory overhead.
-
----
-
-## 📊 Comparison & Examples
-
-
 <p align="center">
-  <em>Left: Regular FIBO (Base Model, CFG=5)&nbsp;&nbsp;|&nbsp;&nbsp;Right: FIBO Lite (Distilled LoRA, CFG=1)</em><br>
-  <img src="assets/astro-pair.png" alt="Comparison" width="100%"/>
+  <img src="https://bria-public.s3.us-east-1.amazonaws.com/car.001.jpeg" width="1024"/>
 </p>
+
 <p align="center">
-  <em>🖼️ More Example Outputs from FIBO Distilled LoRA:</em>
+  <b>FIBO is the first open-source, JSON-native text-to-image model trained exclusively on long structred captions.</b>
+  <br><br>
+  <i>Fibo sets a new standard for controllability, predictability, and disentanglement.</i>
 </p>
-<table>
-  <tr>
-    <td align="center"><img src="assets/gorilla.png"  width="100% "/></td>
-    <td align="center"><img src="assets/sheeps.png"  width="100%"/></td>
-  </tr>
-  <tr>
-    <td align="center"><img src="assets/1.png"  width="100%"/></td>
-    <td align="center"><img src="assets/2.png"  width="100%"/></td>
-  </tr>
-  <tr>
-    <td align="center"><img src="assets/flowers.png"  width="100%"/></td>
-    <td align="center"><img src="assets/41.jpg"  width="100%"/></td>
-  </tr>
-
-</table>
-
-
-| Feature | Base FIBO | FIBO + Distill LoRA |
-| :--- | :---: | :---: |
-| **Guidance Scale** | 5.0 (Typical) | **1.0** (Distilled) |
-| **Compute per Step** | 2x (Cond + Uncond) | **1x (Cond Only)** |
-| **Speed** | Baseline | **~2x Faster** |
-| **Quality** | Full Quality | Slight Degradation |
-
----
-
-## 🛠️ Usage
-
-### Requirements
 
-```bash
-pip install git+https://github.com/huggingface/diffusers torch torchvision  boltons ujson sentencepiece accelerate transformers
-```
-for using gemini api, you need to install `google-genai` as well
 
-### Quick Start
+# Fibo MLX 4-bit
 
-```python
-import os
+This is an 4-bit quantization of [FIBO](https://huggingface.co/briaai/FIBO) made with [mflux](https://github.com/filipstrand/mflux).
 
-import torch
-from diffusers import BriaFiboPipeline
-from diffusers.modular_pipelines import ModularPipeline
+## Run SOTA on Your Mac
 
-# -------------------------------
-# Load the VLM pipeline
-# -------------------------------
-torch.set_grad_enabled(False)
+This quantization brings the state-of-the-art capabilities of FIBO to your local machine. Thanks to the 4-bit quantization and FIBO's efficient architecture, you can now run this powerful 8-billion-parameter model directly on your Mac with excellent performance and reduced memory usage.
 
-# Using local VLM
-vlm_pipe = ModularPipeline.from_pretrained("briaai/FIBO-VLM-prompt-to-JSON", trust_remote_code=True)
+## About the Project
 
+### FIBO
+[FIBO](https://huggingface.co/briaai/FIBO) is an 8B parameter DiT-based, flow-matching text-to-image model designed for enterprise-ready applications. It focuses on:
+- **Controllability & Predictability**: Exceptional prompt adherence using long, structured JSON captions.
+- **Responsible AI**: Trained exclusively on licensed data.
+- **Architecture**: Features SmolLM3-3B as the text encoder and Wan 2.2 as the VAE.
 
-# Using Gemini API, requires GOOGLE_API_KEY environment variable
-# assert os.getenv("GOOGLE_API_KEY") is not None, "GOOGLE_API_KEY environment variable is not set"
-# vlm_pipe = ModularPipeline.from_pretrained("briaai/FIBO-gemini-prompt-to-JSON", trust_remote_code=True)
-
-
-
-# Load the FIBO pipeline
-pipe = BriaFiboPipeline.from_pretrained(
-    "briaai/Fibo-lite",
-    torch_dtype=torch.bfloat16,
-)
-pipe.to("cuda")
-
-# Generate with guidance_scale=1.0 (2x faster!)
-output = vlm_pipe(
-    prompt="A hyper-detailed, ultra-fluffy owl sitting in the trees at night, looking directly at the camera with wide, adorable, expressive eyes. Its feathers are soft and voluminous, catching the cool moonlight with subtle silver highlights. The owl's gaze is curious and full of charm, giving it a whimsical, storybook-like personality."
-)
-json_prompt_generate = output.values["json_prompt"]
-
-def get_default_negative_prompt(existing_json: dict) -> str:
-    negative_prompt = ""
-    style_medium = existing_json.get("style_medium", "").lower()
-    if style_medium in ["photograph", "photography", "photo"]:
-        negative_prompt = """{'style_medium':'digital illustration','artistic_style':'non-realistic'}"""
-    return negative_prompt
-
-
-negative_prompt = get_default_negative_prompt(json.loads(json_prompt_generate))
-results_generate = pipe(
-    prompt=json_prompt_generate, num_inference_steps=50, guidance_scale=1, negative_prompt=negative_prompt
-)
-results_generate.images[0].save("image_generate.png")
-with open("image_generate_json_prompt.json", "w") as f:
-    f.write(json_prompt_generate)
-```
-
-### Key Parameters
-
-- **`guidance_scale=1.0`**: This is the magic setting! With the LoRA loaded, you get the quality of CFG=5 at the speed of CFG=1.
-- **`num_inference_steps=50`**: Standard for FIBO. Adjust based on your quality/speed tradeoff.
-- **No negative prompt needed**: The distillation handles this internally.
-
-
----
-
-## 🧠 Training Details
-
-*   **Method**: Guidance Distillation (Distilling the CFG effect into the model weights via LoRA).
-*   **Base Model**: [briaai/FIBO](https://huggingface.co/briaai/FIBO)
-*   **Trainable Parameters**: 471,472,128
-*   **Precision**: bfloat16
-*   **Teacher Configuration**: CFG=5.0 (standard FIBO setting)
-*   **Student Configuration**: CFG=1.0 (target deployment)
-*   **Training Objective**: Minimize KL divergence between teacher and student outputs
-
-### Training Process
-
-This model was trained to minimize the difference between:
-- **Teacher Model**: Base FIBO running at `guidance_scale=5.0`
-- **Student Model**: Base FIBO + LoRA running at `guidance_scale=1.0`
-
-The training process effectively "bakes in" the stylistic and structural benefits of classifier-free guidance without the computational cost at inference time.
-
----
-
-## 🤝 Community & Support
-
-- **GitHub**: [FIBO Repository](https://github.com/Bria-AI/FIBO)
-- **Hugging Face**: [FIBO Model Card](https://huggingface.co/briaai/FIBO)
-- **Commercial Licensing**: [Contact Bria AI](https://bria.ai/contact-us)
-
----
-
-## 📚 Citation
-
-If you use this model in your research or project, please cite:
-
-```bibtex
-@misc{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 Mokady, Ron},
-  year          = {2025},
-  eprint        = {2511.06876},
-  archivePrefix = {arXiv},
-  primaryClass  = {cs.CV},
-  doi           = {10.48550/arXiv.2511.06876},
-  url           = {https://arxiv.org/abs/2511.06876}
-}
-```
-
----
-
-## 📄 License
+### Mflux
+[Mflux](https://github.com/filipstrand/mflux) is a powerful generation framework built on top of Apple's MLX. It enables efficient inference of diffusion models on Apple Silicon, unlocking the full potential of your Mac's hardware.
 
-<p><b>Source-Code & Weights</b></p>
+## License & Access
 
-<ul>
-  <li>The model is open source for non-commercial use with <a href="https://creativecommons.org/licenses/by-nc/4.0/deed.en">this license</a> </li>
-  <li>For commercial use <a href="https://bria.ai/contact-us?hsCtaAttrib=114250296256">Click here</a>.</li>
-</ul>
-    
+The weights for the original FIBO model are open source for non-commercial use. Please refer to the [original model card](https://huggingface.co/briaai/FIBO) for access and license details.