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
Download provenance.json from FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree: direct link, hf CLI and curl.
- Browser
- Download file 986 Bytes
-
https://huggingface.co/FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree/resolve/main/provenance.json
- Command line
-
hf download hf://FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree/provenance.json
-
curl -L -o provenance.json https://huggingface.co/FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree/resolve/main/provenance.json
986 Bytes
| { | |
| "schema_version": "fasth3-checkpoint-provenance-v1", | |
| "model_id": "FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree", | |
| "base_model": "hf://MiniMaxAI/MiniMax-H3@9bfb6693f2cf6de171db46d1aa586f67d773a1da", | |
| "training_run_id": "20260823T132231Z-v10p5-datafree-sp4", | |
| "wandb_url": "https://wandb.ai/wlsaidhi/h3-dmd2-vsa/runs/a1etree2", | |
| "checkpoint_step": 1300, | |
| "checkpoint_content_sha256": "b36987515e4c75fa4c7aaa632a7842c829ea141b235358a54d782b51230497b3", | |
| "checkpoint_metadata_sha256": "dcad0fbee2a7c7e75e53435f4fd98fccf3138844883874edf057962ab48fa428", | |
| "fastvideo_commit": "48a047c05ff4138f20cfa33351499c6ec5945f5d", | |
| "student_tensor_count": 688, | |
| "student_tensor_bytes": 70099502592, | |
| "student_dtype": "bfloat16", | |
| "dmd_denoising_steps": [999, 749, 500, 250], | |
| "attention_backend": "VIDEO_SPARSE_ATTN_H3", | |
| "vsa_tile_size": 64, | |
| "vsa_sparsity": 0.9, | |
| "known_recipe_deviation": "Predates later continuous score-clock and FastGen-alignment corrections." | |
| } | |