Diffusers
Safetensors
MiniMax H3
video-generation
reference-to-video
text-to-audio-video
fastvideo
fasth3-omni
nvfp4
qad
Instructions to use FastVideo/FastH3-Omni-NVFP4-QAD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FastVideo/FastH3-Omni-NVFP4-QAD 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/FastH3-Omni-NVFP4-QAD", 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
2 days ago
-
Add NVIDIA FastGen team acknowledgement
Verified signaturef01e6a2 -
Add Nuva Lab acknowledgement and link (#1)
- Add Nuva Lab acknowledgement and link (5d57d6775611d3fc7e49e2ca95a061f0a470097c) Co-authored-by: JD <whatif-jd@users.noreply.huggingface.co>c169cf5 -
Use FastH3 Omni name and add local AI recipes
Verified signature0087718 -
Finalize FastH3 OmniRef release model card
Verified signatured0e3679 -
[docs]: production-ready NVFP4 QAD model card
Verified signatureb81e1bf
4 days ago
-
Add the full inference stack: encoder, VAEs, decoders and configs
Verified signature3334982 -
Update the model card for the full v2 release
Verified signaturef5af0cc
5 days ago
-
Add files using upload-large-folder tool
Verified signature4ed3c37 -
initial commit
Verified signature91871c3