Diffusers
Safetensors
MiniMax H3
video-generation
reference-to-video
text-to-audio-video
fastvideo
fasth3-omni
Instructions to use FastVideo/FastVideo-FastH3-Omni-8-Step-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FastVideo/FastVideo-FastH3-Omni-8-Step-V1 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-Omni-8-Step-V1", 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 export_manifest.json from FastVideo/FastVideo-FastH3-Omni-8-Step-V1: direct link, hf CLI and curl.
- Browser
- Download file 776 Bytes
-
https://huggingface.co/FastVideo/FastVideo-FastH3-Omni-8-Step-V1/resolve/main/export_manifest.json
- Command line
-
hf download hf://FastVideo/FastVideo-FastH3-Omni-8-Step-V1/export_manifest.json
-
curl -L -o export_manifest.json https://huggingface.co/FastVideo/FastVideo-FastH3-Omni-8-Step-V1/resolve/main/export_manifest.json
776 Bytes
| { | |
| "attention_backend": "VIDEO_SPARSE_ATTN_H3", | |
| "audio_scheduler_shift": 3.0, | |
| "base_model_revision": "hf://MiniMaxAI/MiniMax-H3@9bfb6693f2cf6de171db46d1aa586f67d773a1da", | |
| "conditioning": "fixed_ordered_references_target_only_flow", | |
| "grid_max_t": 0.999, | |
| "guidance_scale": 1.0, | |
| "model_type": "ref2va", | |
| "num_inference_steps": 8, | |
| "pdd_step_indices": [ | |
| 0, | |
| 4, | |
| 8, | |
| 12, | |
| 16, | |
| 20, | |
| 24, | |
| 28, | |
| 32 | |
| ], | |
| "pdd_steps": 32, | |
| "schema": "fasth3-inference-contract-v1", | |
| "schema_version": "fasth3-inference-contract-v1", | |
| "transformer_component": "transformer_ref", | |
| "transformer_forwards": 8, | |
| "video_scheduler_shift": 12.0, | |
| "vsa_ref_keep_rate": 0.1, | |
| "vsa_ref_policy": "p2_multi_region", | |
| "vsa_sparsity": 0.9, | |
| "vsa_tile_size": 128 | |
| } | |