Instructions to use Kijai/WanVideo_comfy_fp8_scaled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Kijai/WanVideo_comfy_fp8_scaled 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
Text encoder.
#17
by lhucklen - opened
InThe comfy wan video wrapped set The node Wan T5 text encoder loader gives an option for quantinization fp8 e4m3fn. I have not been able to find this model on hugging face. Specifically, umt5 xxl fp8 e4m3fn Variant. There is a scaled version but the text encoder in the wan video wrapper nodes does not support it.