Text-to-Video
MLX
Diffusers
Safetensors
English
Chinese
apple-silicon
video-generation
image-to-video
video-continuation
longcat
flow-matching
block-sparse-attention
Instructions to use mlx-community/LongCat-Video-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/LongCat-Video-bf16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir LongCat-Video-bf16 mlx-community/LongCat-Video-bf16
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "_class_name": "LongCatVideoTransformer3DModel", | |
| "_diffusers_version": "0.32.0", | |
| "adaln_tembed_dim": 512, | |
| "bsa_params":{ | |
| "sparsity": 0.9375, | |
| "chunk_3d_shape_q": [4, 4, 4], | |
| "chunk_3d_shape_k": [4, 4, 4] | |
| }, | |
| "caption_channels": 4096, | |
| "cp_split_hw": null, | |
| "depth": 48, | |
| "enable_bsa": false, | |
| "enable_flashattn3": false, | |
| "enable_flashattn2": true, | |
| "frequency_embedding_size": 256, | |
| "hidden_size": 4096, | |
| "in_channels": 16, | |
| "text_tokens_zero_pad": true, | |
| "mlp_ratio": 4, | |
| "num_heads": 32, | |
| "out_channels": 16, | |
| "patch_size": [ | |
| 1, | |
| 2, | |
| 2 | |
| ] | |
| } | |