Instructions to use Arrexel/pattern-diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Arrexel/pattern-diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Arrexel/pattern-diffusion", 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
- Local Apps
- Draw Things
- DiffusionBee
Pattern Diffusion WebUI
#2
by mnemic - opened
Nice work!
I created a small webUI for it:
https://github.com/MNeMoNiCuZ/pattern-diffusion-webui
Feel free to link to it or steal the code if you want it.
Awesome! Just one note, the disable_seamless calls should be moved inside the for loop so that it is disabled at the start of every pipe call in the batch
Thanks for the input. Updated with this change.