README.md

metadata

title: FastH3-Omni
emoji: 🎬
colorFrom: blue
colorTo: indigo
sdk: gradio
sdk_version: 6.30.0
app_file: app.py
python_version: '3.12'
pinned: false
short_description: FastVideo 8-step video+audio from image/video/audio refs
startup_duration_timeout: 1h
models:
  - FastVideo/FastVideo-FastH3-Omni-8-Step-V1
  - FastVideo/FastH3-Omni-Comfy
  - FastVideo/FastH3-Omni-FP8
  - FastVideo/FastH3-Omni-NVFP4-QAD
  - FastVideo/FastH3-NVFP4-VAE-Decoder
  - FastVideo/FastH3-Omni-FP8-Comfy
  - FastVideo/FastH3-Omni-NVFP4-QAD-Comfy
  - MiniMaxAI/MiniMax-H3

FastH3-Omni

FastVideo's 8-step FastH3-Omni student of MiniMax-H3 on ZeroGPU: ordered image, video and audio references plus a prompt become a short clip with a matching soundtrack. Runs the FP8 W8A8 export (FastVideo/FastH3-Omni-FP8) with FastVideo's Triton tile-64 block-sparse attention, and restores its compiled kernels from multimodalart/fasth3-omni-kernel-cache at startup so the first call doesn't JIT-compile.

The prompt composer is a custom gr.HTML component (composer.html / composer.css / composer.js): references get <Picture n> / <Video n> / <Audio n> tags as they are added, and the prompt is either assembled by the six-section H3 builder or written by hand with those tags. "Upsample" rewrites it through hugging-apps/minimax-h3-prompt-rewriter.

FastVideo is installed from a wheel of hao-ai-lab/FastVideo@376e445f whose unused gradio==5.32.0 pin is relaxed, so the Space runs Gradio 6.

All checkpoints: FastH3-Omni collection.