Text-to-Video
Diffusers
Safetensors
MiniMax H3
video
audio
text-to-audio-video
distillation
dmd2
few-step
fastvideo
fasth3
preview
Instructions to use FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Commit History
-
[docs]: restore Hugging Face download tracking
Verified signatureSet the model card library_name to diffusers so Hugging Face uses the registered query-file rule for this artifact layout.5ea076f
-
docs: add linked FastH3 acknowledgements
Verified signatureb65818d -
[docs] fix FastH3 installation instructions
Verified signature076b953 -
[docs] simplify FastH3 model card
Verified signaturecd8c735 -
[docs] add FastVideo logo to model card
Verified signature1b0dbe4
-
[docs]: document the FastH3 VSA kernel requirement
Verified signatureState prominently that this checkpoint requires FastVideo VSA-H3 and the Video Sparse Attention kernel.b06b101 -
[docs]: align FastH3 Preview v1 naming
Verified signatureUpdate the model card and package self-references after the server-side repository rename.cf2917a -
[model]: document v10.5 checkpoint provenance
Verified signatureb790390 -
Add files using upload-large-folder tool
Verified signature8b09666 -
Add files using upload-large-folder tool
Verified signature379da9c -
initial commit
Verified signaturee0f9972