How to use BiliSakura/PixelFlow-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("BiliSakura/PixelFlow-diffusers", dtype=torch.bfloat16, device_map="cuda") prompt = "golden retriever" image = pipe(prompt).images[0]
https://huggingface.co/BiliSakura/PixelFlow-diffusers/resolve/main/PixelFlow-256/transformer/__pycache__/modeling_pixelflow.cpython-312.pyc
hf download hf://BiliSakura/PixelFlow-diffusers/PixelFlow-256/transformer/__pycache__/modeling_pixelflow.cpython-312.pyc
curl -L -o modeling_pixelflow.cpython-312.pyc https://huggingface.co/BiliSakura/PixelFlow-diffusers/resolve/main/PixelFlow-256/transformer/__pycache__/modeling_pixelflow.cpython-312.pyc
