Instructions to use maxin-cn/Latte-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use maxin-cn/Latte-1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("maxin-cn/Latte-1", 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
Link model to paper page
#1
by nielsr HF Staff - opened
Hi,
Niels here from the open-source team at HF. Thanks for sharing the model on the hub!
This PR links it to the paper: https://huggingface.co/papers/2401.03048.
Also, it'd be great to remove the weights from the Space: https://huggingface.co/spaces/maxin-cn/Latte-1, and instead use the weights from this model repo (we don't recommend pushing weights to a Space repo).
Cheers,
Niels
Ok! Thanks for your mention.
maxin-cn changed pull request status to merged