Instructions to use FastVideo/FastH3-Omni-Comfy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use FastVideo/FastH3-Omni-Comfy 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
Commit History
Yesterday
-
Add NVIDIA FastGen team acknowledgement
Verified signature82eff2a -
Add Nuva Lab acknowledgement and link (#1)
- Add Nuva Lab acknowledgement and link (9bf784c899591e8026c6f09a586963dbb90f1747) Co-authored-by: JD <whatif-jd@users.noreply.huggingface.co>c6e7d1f -
Use FastH3 Omni name and add local AI recipes
Verified signaturef519722 -
Finalize FastH3 OmniRef release model card
Verified signaturecd0bc88 -
[docs]: production-ready Comfy model card
Verified signature3ed310f -
Add native ComfyUI OmniRef checkpoints
Verified signaturePackage canonical OmniRef BF16 with rank-8 AdaLN curves and reuse the verified Comfy-produced INT8 payload unchanged. Copy pinned shared Comfy text encoders and VAEs. Include conversion code, hashes, source matching and explicit validation limits.2f48fc1