ComfyUI Extension: ComfyUI_Dif_GGUF
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Easy quant comfyUI origin model to gguf , and esay use it, save more disk...
Looking for a different extension?
Custom Nodes (0)
README
ComfyUI_Dif_GGUF
Easy quant comfyUI origin models to gguf , and esay use it, save more disk...
Tips
- find it in model/loader,replace the original unet_loader to gguf_loader
- 节点在模型/加载目录下,对于大部分单unet加载的,替换原始unet加载器为gguf加载器即可,hidream-O1 暂时未支持
1.Installation
In the ./ComfyUI/custom_nodes directory, run the following:
git clone https://github.com/smthemex/ComfyUI_Dif_GGUF
2.requirements
If you have gguf install,don't need to install requirements.txt
pip install -r requirements.txt
3.checkpoints
Any diffusion gguf,for example :
klein9b
comfy-org-gguf
├── ComfyUI/models/
| ├── diffusion_models/
| ├──Flux2-Klein-9B-True-V3-Q8_0.gguf # optional
| ├── gguf/
| ├──Flux2-Klein-9B-True-V3-Q8_0.gguf # optional
4.Example
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.