Quanta AI Labs

Hao AI Lab @ UCSD · Text-to-Video

FastWan

FastWan is a family of video generation models using sparse distillation to generate 5-second videos in 5 seconds on H200 GPUs. The approach combines Video Sparse Attention (VSA) with extreme diffusion compression to overcome attention bottlenecks in multi-step video synthesis.

Open the source ↗

Similar Video & Animation releases

  • Genie 4

    Google DeepMind · Interactive world model · Week 45, 2026

  • FastH3 Omni speed results

    Hao AI Lab @ UCSD · Fast Video Model · Week 44, 2026

  • Hy-Nomas

    Tencent Hunyuan · World Model · Week 44, 2026

  • GWM Worlds 2

    Runway · Interactive World Model · Week 36, 2026

  • Unreel

    blendi-remade · Real-Time AI Streaming · Week 36, 2026

  • H3-World Action Demo

    hugging-apps · Action-Conditioned World Model · Week 36, 2026

More from Hao AI Lab @ UCSD

Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.