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:
hugging-apps
/
h3-world-action-demo
Running on Zero

App Files Files Community
1
Fetching metadata from the HF Docker repository...
h3-world-action-demo
512 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 8 commits
multimodalart's picture
multimodalart HF Staff
Fold larryvrh/MiniMax-H3-Turbo-Lora v4-600-EMA instead of the lightx2v 8-step file
d53b4b0 verified about 1 month ago
  • assets
    H3-World: action-conditioned world model with the directed attention mask about 1 month ago
  • .gitattributes
    1.71 kB
    H3-World: action-conditioned world model with the directed attention mask about 1 month ago
  • README.md
    11 kB
    Add a 28-step vs 8-step turbo LoRA sampling choice (lightx2v/Minimax-h3-Turbo) about 1 month ago
  • app.py
    52.6 kB
    Rewrite the intro, draw the action legend as keycaps, drop the Sampling blurb, swap in larryvrh's v4 turbo LoRA about 1 month ago
  • h3_split_blocks.py
    6.53 kB
    H3-World: action-conditioned world model with the directed attention mask about 1 month ago
  • h3_turbo_lora.py
    9.73 kB
    Fold larryvrh/MiniMax-H3-Turbo-Lora v4-600-EMA instead of the lightx2v 8-step file about 1 month ago
  • requirements.txt
    1.04 kB
    H3-World: action-conditioned world model with the directed attention mask about 1 month ago