Instructions to use camenduru/potat1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use camenduru/potat1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("camenduru/potat1", 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
Stretched horizontally
#3
by tintwotin - opened
Try to render a video with the prompt: "a football on grass".
For me(using colab), it comes stretched horizontally. It might be the same problem here: https://github.com/ExponentialML/Text-To-Video-Finetuning/discussions/68Cool, I didn't know about that discord. Thanks. I see a lot of the same people from Deforum are hanging out there. Chatted with Cerspence about this problem yesterday. Small world. :-)