Instructions to use noctuashap/LongCat-Video-I2V-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use noctuashap/LongCat-Video-I2V-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("noctuashap/LongCat-Video-I2V-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
Upload LongCat weights: LongCat Video Image-to-Video model in FastVideo/Diffusers format
db99e98 verified - Xet hash:
- e9d3dbccacd4303e4cdfabc1c9c486b0c14809a57ed60cab7e245c267c2763c0
- Size of remote file:
- 2.89 GB
- SHA256:
- 7e76e18d224531b8197a46231cb53daf7f2f6ca707130252becf933026ac4eea
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.