Instructions to use Comfy-Org/Wan_2.1_ComfyUI_repackaged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Comfy-Org/Wan_2.1_ComfyUI_repackaged with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Error with workflow in Comfy 3.18
I'm having some trouble with this workflow. Any idea what the issue might be? I think I have all the right models and files. I keep getting a "reconnecting" error followed by a token error. It's being hosted on a virtual-machine with a 48GB GPU, running Comfy 3.18. Thanks if anyone can help. I'm using the img2vid 720p json workflow.
Wrong text encoder, use the one from this repo instead.
I tried the 16bit one several times but I keep getting this "Reconnecting... " error. After I get that, if I try again, I get a token error. Thanks if anyone can help. I am running Comfy on a virtual machine if that makes any difference.
same eror for me
As mentioned above the text encode is wrong. It's a thingy going inside "Load CLIP". On the screenshots it's wrong.
Had some error. This one worked for me: umt5_xxl_fp16.safetensors (from this site)