ComfyUI Extension: ComfyUI-DFloat11
This repository provides the ComfyUI plugin for DFloat11 models. DFloat11 reduces model size by more than 30% while producing bit-for-bit identical outputs to the original. Unlike quantization techniques which trade quality for size, DFloat11 is a lossless compression method, preserving model output quality fully while supporting efficient inference.
Custom Nodes (0)
README
ComfyUI Plugin for DFloat11
This repository provides the ComfyUI plugin for DFloat11 models.
DFloat11 reduces model size by more than 30% while producing bit-for-bit identical outputs to the original. Unlike quantization techniques which trade quality for size, DFloat11 is a lossless compression method, preserving model output quality fully while supporting efficient inference.
Currently, only FLUX.1 models are supported. Support for additional models is planned. Please feel free to open an issue and let us know which ones you'd like to see next.
Features
- 🚀 Fully Lossless – 100% identical outputs to the original model
- 📦 >30% smaller model size – lower VRAM requirements than the original model
- ⚡ Compatible with ComfyUI – drop-in support with custom nodes
- 🔧 GPU-accelerated inference – optimized for CUDA 12.1+
Installation
Requirements
- ComfyUI installed
- NVIDIA GPU with CUDA 12.1+
Setup
-
Install dependencies:
pip install -r requirements.txt
-
Install the DFloat11 custom nodes in ComfyUI:
cd <ComfyUI_installation_path>/custom_nodes git clone https://github.com/LeanModels/ComfyUI-DFloat11.git
Usage
- Once installed, the DFloat11 nodes show up under the
DFloat11
folder in the Node Library. - Download a DFloat11 model for ComfyUI from Hugging Face and place it under
<ComfyUI_installation_path>/models/diffusion_models
. - Drag and drop a
*.png
or*.json
file from workflows into ComfyUI to load the workflow. - (Optional) Use the
DFloat11 Model Loader
node to load the model in*.safetensors
format, which acts as a drop-in replacement for theLoad Diffusion Model
node.
Resources
Contributing
Contributions are welcome!
- Open an issue to request new model support
- Submit pull requests for bug fixes or improvements