Text-to-Image
Diffusers
Safetensors
PixArtAlphaPipeline
Pixart-α
PixArt-XL-2-1024-MS / README.md
yujincheng08's picture
Update README.md
196525a
|
raw
history blame
387 Bytes
metadata
license: cc-by-nc-4.0

Usage:

from diffusers import PixArtAlphaPipeline
import torch
pipe = PixArtAlphaPipeline.from_pretrained("PixArt-alpha/PixArt-XL-2-1024-MS", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
pipe.enable_attention_slicing()
prompt = "A alpaca made of colorful building blocks, cyberpunk"
images = pipe(prompt).images
images[0].save('test.png')