Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Spaces:
avila110
/
infinitetalk
Running on Zero

App Files Files Community
Fetching metadata from the HF Docker repository...
infinitetalk / wan /modules
146 kB
Ctrl+K
Ctrl+K
  • 2 contributors
History: 9 commits
Daniel
Fix OOM and extreme lag by bypassing unused reference attention in single-human mode and chunking multi-human reference attention
03a50fa 3 days ago
  • __init__.py
    422 Bytes
    Deploy InfiniteTalk Gradio Demo with ZeroGPU support 4 days ago
  • attention.py
    19.6 kB
    Accelerate flash_attention using xformers Cutlass and contiguous SDPA kernels 3 days ago
  • clip.py
    16.8 kB
    Deploy InfiniteTalk Gradio Demo with ZeroGPU support 4 days ago
  • model.py
    21.4 kB
    Fix tensor device mismatch between cuda and cpu in SDPA fallback 3 days ago
  • multitalk_model.py
    30.6 kB
    Fix OOM and extreme lag by bypassing unused reference attention in single-human mode and chunking multi-human reference attention 3 days ago
  • t5.py
    18 kB
    Fix CUDA re-init in forked subprocess: defer model imports & lazy xformers 4 days ago
  • tokenizers.py
    2.43 kB
    Deploy InfiniteTalk Gradio Demo with ZeroGPU support 4 days ago
  • vace_model.py
    8.32 kB
    Fix tensor device mismatch between cuda and cpu in SDPA fallback 3 days ago
  • vae.py
    23.2 kB
    Deploy InfiniteTalk Gradio Demo with ZeroGPU support 4 days ago
  • xlm_roberta.py
    4.87 kB
    Deploy InfiniteTalk Gradio Demo with ZeroGPU support 4 days ago