infinitetalk / wan /utils /multitalk_utils.py

Commit History

3 days ago

  1. Fix OOM and extreme lag by bypassing unused reference attention in single-human mode and chunking multi-human reference attention Running

    Daniel
    03a50fa
  2. Optimize ZeroGPU duration to 300s, set recommended 15 steps, and remove torch.compile lag

    Daniel
    d05af4e
  3. Fix tensor device mismatch between cuda and cpu in SDPA fallback

    Daniel
    85175b0

4 days ago

  1. Disable empty_cache during diffusion loop to prevent dynamo handler collision

    Verified signature
    a8ab186
  2. Fix CUDA re-init in forked subprocess: defer model imports & lazy xformers

    Verified signature
    e579ffb
  3. Fix ZeroGPU compatibility: mock gcnArchName and decouple xfuser

    Verified signature
    fcb6a26
  4. Deploy InfiniteTalk Gradio Demo with ZeroGPU support

    Verified signature
    13c793c