Update README.md

README.md

@@ -13,50 +13,40 @@ tags:
   - diffusion-single-file
 pipeline_tag: image-to-image
 ---
+
 # flux1-kontext-dev-fp8
 
-This repository provides FP8-quantized weights for [black-forest-labs/FLUX.1-Kontext-dev](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev). Both E4M3FN and E5M2 FP8 formats are available.
+FP8-quantized weights for [FLUX.1-Kontext-dev](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev) diffusion models. Supports both E4M3FN and E5M2 formats.
 
 ## Model Overview
-
-- **Source model:** [black-forest-labs/FLUX.1-Kontext-dev](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev)
-- **Quantization:** All weights are converted to FP8 (float8_e4m3fn and float8_e5m2) for reduced storage and memory usage.
-- **Intended use:** For research and testing on hardware and software stacks supporting FP8 (PyTorch 2.4+, CUDA 12.4+, Hopper/Ada GPUs).
-- **Disclaimer:** FP8 quantization may lead to reduced inference quality. Not all software/hardware supports FP8.
-
-## Key Features
-
-1. **FP8 Quantization:** Weights are provided in both E4M3FN and E5M2 FP8 formats for maximum compatibility and efficiency.
-2. **Storage & Memory Efficient:** Significantly reduces model file size and GPU memory usage compared to float16/bfloat16.
-3. **ComfyUI Compatible:** Ready to use with [ComfyUI](https://github.com/comfyanonymous/ComfyUI) and other frameworks supporting FP8.
-
-## Files
-
-- flux1-kontext-dev-fp8-e4m3fn.safetensors — FP8 (E4M3FN) quantized weights
-- `flux1-kontext-dev-fp8-e5m2.safetensors` — FP8 (E5M2) quantized weights
-
-## Usage (Recommended: ComfyUI)
-
-We recommend using these weights with [ComfyUI](https://github.com/comfyanonymous/ComfyUI) and its FP8 support.  
-To use:
-
-1. Place the `.safetensors` file in your ComfyUI models directory.
-2. Make sure your ComfyUI and PyTorch installation support FP8 (PyTorch 2.4+, CUDA 12.4+, Hopper/Ada GPU).
-3. Select the FP8 model in your ComfyUI workflow as you would with standard weights.
-
-## Credits
-
-- Original model by [black-forest-labs](https://huggingface.co/black-forest-labs)
-
-# License
-This model falls under the [FLUX.1 \[dev\] Non-Commercial License](https://github.com/black-forest-labs/flux/blob/main/model_licenses/LICENSE-FLUX1-dev).
-
-# Citation
-
+- **Base Model**: [FLUX.1-Kontext-dev](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev) (diffusion model component)
+- **Quantization**: Per-tensor dynamic quantization to FP8 (E4M3FN/E5M2)
+- **Size Reduction**: ~40% smaller than original weights
+- **Model Scope**: This is **only the diffusion_model** component (not full pipeline), should be placed in ComfyUI's `diffusion_models` directory
+- **Compatibility**: 
+  - ✅ ComfyUI (with PyTorch 2.4+ and CUDA 12.4+)
+  - ❌ Diffusers (currently unsupported)
+
+## Available Files
+- `flux1-kontext-dev-fp8-e4m3fn.safetensors` - Balanced performance/accuracy
+- `flux1-kontext-dev-fp8-e5m2.safetensors` - Higher throughput on Hopper GPUs
+
+## Usage
+1. Move the `.safetensors` file to your ComfyUI `diffusion_models` directory
+2. Select fp8 modes in UNet Loader like `fp8_e4m3fn`.
+
+## Known Limitations
+1. Not compatible with standard Diffusers pipelines
+2. Requires patched PyTorch versions for optimal performance
+
+## License
+This model is distributed under the [FLUX.1(dev) Non-Commercial License](https://github.com/black-forest-labs/flux/blob/main/model_licenses/LICENSE-FLUX1-dev). Commercial use prohibited without authorization.
+
+## Citation
 ```bib
 @misc{labs2025flux1kontextflowmatching,
-      title={FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space}, Add commentMore actions
-      author={Black Forest Labs and Stephen Batifol and Andreas Blattmann and Frederic Boesel and Saksham Consul and Cyril Diagne and Tim Dockhorn and Jack English and Zion English and Patrick Esser and Sumith Kulal and Kyle Lacey and Yam Levi and Cheng Li and Dominik Lorenz and Jonas Müller and Dustin Podell and Robin Rombach and Harry Saini and Axel Sauer and Luke Smith},
+      title={FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space},
+      author={Black Forest Labs et al.},
       year={2025},
       eprint={2506.15742},
       archivePrefix={arXiv},