Image-to-Video
Diffusion Single File
text-to-video
image-text-to-video
video-to-video
text-to-audio-video
image-to-audio-video
image-text-to-audio-video
video-to-audio-video
audio-to-audio-video
audio-video-generation
multimodal
synchronized-audio-video
reference-to-audio-video
Instructions to use rzgar/FastVideo-FastH3-Motion-Enhanced-Comfy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use rzgar/FastVideo-FastH3-Motion-Enhanced-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
speed is the same as normal h3
#1
by ZKong - opened
Thanks again for your model. when using your workflow I get a log from comfyui.
'[INFO] VSA: extra_tokens ignored (the trained sparse pattern is the target)'
I heard the fastvideo twice the speed using vsa attention, but result not as that fast
You're welcome,
You can switch to the default workflow to see if the issue is the workflow. However, I’m seeing the boost.
Default workflow: https://raw.githubusercontent.com/Comfy-Org/workflow_templates/main/templates/video_fastvideo_fasth3_i2v.json
info: https://comfyui-wiki.com/en/news/2026-09-16-fasth3-comfyui-templates
maybe only for 50s card, i am 40s. PS fastvieo only for t2v,i just know, not that useful
ZKong changed discussion status to closed
