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

yslan
/
Track4D-2026

Video-to-Video
Diffusers
video
tracking
3d
wan
Model card Files Files and versions
xet
Community

Instructions to use yslan/Track4D-2026 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Diffusers

    How to use yslan/Track4D-2026 with Diffusers:

    pip install -U diffusers transformers accelerate
    import torch
    from diffusers import DiffusionPipeline
    
    # switch to "mps" for apple devices
    pipe = DiffusionPipeline.from_pretrained("yslan/Track4D-2026", dtype=torch.bfloat16, device_map="cuda")
    
    prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
    image = pipe(prompt).images[0]
  • Notebooks
  • Google Colab
  • Kaggle
Track4D-2026 / evaluation
Ctrl+K
Ctrl+K
  • 1 contributor
History: 4 commits
yslan's picture
yslan
Add aligned Stream3R short256 49-frame evaluation NPZ assets
1ce38c0 verified about 1 month ago
  • da3base_step012500_predictions
    Add exact DA3 step 12.5K prediction NPZ metric replay about 1 month ago
  • dense2d_step011500
    Add exact dense 2D step 11.5K metrics NPZ and visualizations about 1 month ago
  • stream3r_short256_49f
    Add aligned Stream3R short256 49-frame evaluation NPZ assets about 1 month ago
  • worldtrack_release
    Add WorldTrack evaluation NPZ assets about 1 month ago