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
Browse filesHi,
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
README.md
CHANGED
|
@@ -34,6 +34,7 @@ If you find this work useful for your research, please consider citing it.
|
|
| 34 |
}
|
| 35 |
```
|
| 36 |
|
|
|
|
| 37 |
|
| 38 |
## Acknowledgments
|
| 39 |
Latte has been greatly inspired by the following amazing works and teams: [DiT](https://github.com/facebookresearch/DiT) and [PixArt-α](https://github.com/PixArt-alpha/PixArt-alpha), we thank all the contributors for open-sourcing.
|
|
|
|
| 34 |
}
|
| 35 |
```
|
| 36 |
|
| 37 |
+
Paper: https://huggingface.co/papers/2401.03048
|
| 38 |
|
| 39 |
## Acknowledgments
|
| 40 |
Latte has been greatly inspired by the following amazing works and teams: [DiT](https://github.com/facebookresearch/DiT) and [PixArt-α](https://github.com/PixArt-alpha/PixArt-alpha), we thank all the contributors for open-sourcing.
|