Instructions to use alibaba-pai/Wan2.2-VACE-Fun-A14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VideoX Fun
How to use alibaba-pai/Wan2.2-VACE-Fun-A14B with VideoX Fun:
# 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
- Wan2.2
How to use alibaba-pai/Wan2.2-VACE-Fun-A14B with Wan2.2:
# 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
Wan2.2-VACE-Fun-A14B in FP32?
#2
by 42hub - opened
Hi,
FP32 -> FP8 gives slightly better quality than BF16 -> FP8
FP16 might be a tiny bit better quality than BF16
Is there any chance Wan2.2-VACE-Fun-A14B weights could be shared in FP32
so that we can produce an FP16 and a better quality FP8 version?
Thx!
Sorry, we didn’t keep the FP32 version.