Instructions to use maxin-cn/Latte with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use maxin-cn/Latte 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", 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
Inquiry on Removing 'shutterstock' Watermark from Generated Videos
Hello Team,
Thanks for the exceptional work you have been contributing to the project.
However, I've encountered an issue. I have noticed that the videos generated contain a 'shutterstock' watermark. I was wondering if there is a way to remove or avoid this watermark in the generated videos.
Thank you for your attention to this matter and for your ongoing support.
Hello Team,
Thanks for the exceptional work you have been contributing to the project.
However, I've encountered an issue. I have noticed that the videos generated contain a 'shutterstock' watermark. I was wondering if there is a way to remove or avoid this watermark in the generated videos.
Thank you for your attention to this matter and for your ongoing support.
This is because every video in webvideo, the training dataset used, contains a "shutterstock" watermark. In LatteT2V, which is currently available, this problem should not be avoided. We will release an unwatermarked version later.
A new model is released. You can try it.