Instructions to use StonyBrook-CVLab/PixCell-256 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use StonyBrook-CVLab/PixCell-256 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("StonyBrook-CVLab/PixCell-256", 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
StonyBrook-CVLab/PixCell-pipeline missing
Hello, I can't find StonyBrook-CVLab/PixCell-pipeline.
I also encountered this problem.
We just made the custom pipeline public. Can you try again?
Thank you for your prompt response. The issue has been resolved. Also, could you please let me know if you have any plans to open-source the Pixcell-512 version of the model?
Hello,
The PixCell-512 model was trained as an intermediate step to scale from 256x256 to 1024x1024 images.
Since we did not train for a full epoch and haven't evaluated the generated image quality as in PixCell-256 and PixCell-1024, we decided not to publish the weights yet.
If you believe that there is value in using the 512x512 model, we'd be happy to publish the weights of that as well.