metadata

language:
  - en
library_name: diffusers
pipeline_tag: text-to-image

You Only Sample Once (YOSO)

The YOSO was proposed in "You Only Sample Once: Taming One-Step Text-To-Image Synthesis by Self-Cooperative Diffusion GANs" by Yihong Luo, Xiaolong Chen, Xinghua Qu, Jing Tang.

Official Repository of this paper: YOSO.

This model is fine-tuning from PixArt-XL-2-512x512, enabling one-step inference to perform text-to-image generation.

We wanna highlight that the YOSO-PixArt was originally trained on 512 resolution. However, we found that we can construct a YOSO that enables generating samples with 1024 resolution by merging with PixArt-XL-2-1024-MS (Section 6.3.1 in the paper). The impressive performance indicates the robust generalization ability of our YOSO.

usage

import torch
from diffusers import PixArtAlphaPipeline, LCMScheduler, Transformer2DModel

transformer = Transformer2DModel.from_pretrained(
    "Luo-Yihong/yoso_pixart1024", torch_dtype=torch.float16).to('cuda')

pipe = PixArtAlphaPipeline.from_pretrained("PixArt-alpha/PixArt-XL-2-512x512", 
                                           transformer=transformer,
                                           torch_dtype=torch.float16, use_safetensors=True)

pipe = pipe.to('cuda')
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
pipe.scheduler.config.prediction_type = "v_prediction"
generator = torch.manual_seed(318)
imgs = pipe(prompt="Pirate ship trapped in a cosmic maelstrom nebula, rendered in cosmic beach whirlpool engine, volumetric lighting, spectacular, ambient lights, light pollution, cinematic atmosphere, art nouveau style, illustration art artwork by SenseiJaye, intricate detail.",
                    num_inference_steps=1, 
                    num_images_per_prompt = 1,
                    generator = generator,
                    guidance_scale=1.,
                   )[0]
imgs[0]

Bibtex

@misc{luo2024sample,
      title={You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs}, 
      author={Yihong Luo and Xiaolong Chen and Xinghua Qu and Jing Tang},
      year={2024},
      eprint={2403.12931},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}