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
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

SceneWorks
/
scail2-mlx

Image-to-Video
Diffusers
MLX
i2v
character-animation
video-generation
cross-identity-replacement
pose-driven
diffusion
apple-silicon
Model card Files Files and versions
xet
Community

Instructions to use SceneWorks/scail2-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Diffusers

    How to use SceneWorks/scail2-mlx with Diffusers:

    pip install -U diffusers transformers accelerate
    import torch
    from diffusers import DiffusionPipeline
    from diffusers.utils import load_image, export_to_video
    
    # switch to "mps" for apple devices
    pipe = DiffusionPipeline.from_pretrained("SceneWorks/scail2-mlx", dtype=torch.bfloat16, device_map="cuda")
    pipe.to("cuda")
    
    prompt = "A man with short gray hair plays a red electric guitar."
    image = load_image(
        "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png"
    )
    
    output = pipe(image=image, prompt=prompt).frames[0]
    export_to_video(output, "output.mp4")
  • MLX

    How to use SceneWorks/scail2-mlx with MLX:

    # Download the model from the Hub
    pip install huggingface_hub[hf_xet]
    
    huggingface-cli download --local-dir scail2-mlx SceneWorks/scail2-mlx
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • LM Studio
scail2-mlx
25.2 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 18 commits
SceneWorks's picture
SceneWorks
sc-5445: ship lean pre-quantized Q4 snapshot (Q4 DiT 32.8->8.9GB + quantization manifest; prune redundant raw pickles; refresh card)
35d6df7 verified 7 days ago
  • umt5-xxl
    sc-5445: ship lean pre-quantized Q4 snapshot (Q4 DiT 32.8->8.9GB + quantization manifest; prune redundant raw pickles; refresh card) 7 days ago
  • .gitattributes
    1.63 kB
    sc-5445: root umt5 tokenizer.json for Umt5Encoder 8 days ago
  • README.md
    6.16 kB
    sc-5445: ship lean pre-quantized Q4 snapshot (Q4 DiT 32.8->8.9GB + quantization manifest; prune redundant raw pickles; refresh card) 7 days ago
  • bias-aware-dpo-lora.pt
    1.23 GB
    xet
    Add bias-aware-dpo-lora.pt 8 days ago
  • clip.safetensors
    2.53 GB
    xet
    sc-5445: converted open-CLIP ViT-H/14 visual tower (f32) for ScailClip 8 days ago
  • config.json
    332 Bytes
    sc-5445: ship lean pre-quantized Q4 snapshot (Q4 DiT 32.8->8.9GB + quantization manifest; prune redundant raw pickles; refresh card) 7 days ago
  • dit.safetensors
    9.58 GB
    xet
    sc-5445: ship lean pre-quantized Q4 snapshot (Q4 DiT 32.8->8.9GB + quantization manifest; prune redundant raw pickles; refresh card) 7 days ago
  • t5_encoder.safetensors
    11.4 GB
    xet
    sc-5445: converted umt5-xxl encoder (bf16) for Umt5Encoder 8 days ago
  • tokenizer.json
    16.8 MB
    xet
    sc-5445: root umt5 tokenizer.json for Umt5Encoder 8 days ago
  • vae.safetensors
    508 MB
    xet
    sc-5445: converted Wan2.1 z16 VAE (f32) for WanVae 8 days ago