Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • 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:
ggamecrazy
/
lyra2-explorable-scene
Paused

App Files Files Community
Fetching metadata from the HF Docker repository...
lyra2-explorable-scene
19 MB
Ctrl+K
Ctrl+K
  • 2 contributors
History: 29 commits
cezar-hapiko's picture
cezar-hapiko
Load model synchronously before Gradio launch (fix HF gcTimeout kill)
405bc15 5 months ago
  • build_support
    Rewrite Dockerfile with uv for Python 3.12 + deps 5 months ago
  • previews
    Fix preview mp4 (was filtered by .gitignore) 5 months ago
  • wheels
    Ship pre-built CUDA wheels (TE+TE_torch/VIPE/DA3/gsplat) via Git LFS 5 months ago
  • .dockerignore
    506 Bytes
    Initial Dockerfile + Gradio UI 5 months ago
  • .gitattributes
    313 Bytes
    Inline sample-04 output preview for pre-filled input 5 months ago
  • .gitignore
    747 Bytes
    Fix preview mp4 (was filtered by .gitignore) 5 months ago
  • Dockerfile
    6.43 kB
    Refactor: load Lyra-2 model once at startup, reuse across requests 5 months ago
  • README.md
    3.45 kB
    Load model synchronously before Gradio launch (fix HF gcTimeout kill) 5 months ago
  • app.py
    15.6 kB
    Load model synchronously before Gradio launch (fix HF gcTimeout kill) 5 months ago
  • download_checkpoints.py
    3.54 kB
    Smarter download_checkpoints: skip download if /data/Lyra-2 already populated (direct model mount) 5 months ago
  • entrypoint.sh
    777 Bytes
    Fix stage-2 OOM: offload Lyra-2 net to CPU during DA3 GS recon 5 months ago
  • resident_inference.py
    32 kB
    Refactor: load Lyra-2 model once at startup, reuse across requests 5 months ago
  • warm_model_test.py
    4.61 kB
    Refactor: load Lyra-2 model once at startup, reuse across requests 5 months ago