PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
Paper • 2310.00426 • Published • 62
How to use cuio/PixArt-alpha with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("cuio/PixArt-alpha", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]These weights are for the original Github repository and it's only for research purpose. For other purposes, please check https://huggingface.co/docs/diffusers/main/en/api/pipelines/pixart and https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS.
Inference Code: https://github.com/PixArt-alpha/PixArt-alpha