Instructions to use FastVideo/LongCat-Video-VC-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FastVideo/LongCat-Video-VC-Diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("FastVideo/LongCat-Video-VC-Diffusers", 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
| { | |
| "_class_name": "LongCatTransformer3DModel", | |
| "_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, | |
| "out_channels": 16, | |
| "patch_size": [ | |
| 1, | |
| 2, | |
| 2 | |
| ], | |
| "num_attention_heads": 32 | |
| } |