README.md

---
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
---
# You Only Sample Once (YOSO)

![overview](overview.jpg)

The YOSO was proposed in "[You Only Sample Once: Taming One-Step Text-To-Image Synthesis by Self-Cooperative Diffusion GANs](https://www.arxiv.org/abs/2403.12931)" by *Yihong Luo, Xiaolong Chen, Xinghua Qu, Jing Tang*. 

Official Repository of this paper: [YOSO](https://github.com/Luo-Yihong/YOSO).

This model is fine-tuning from [
PixArt-XL-2-512x512](https://huggingface.co/PixArt-alpha/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](https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS
) (Section 6.3.1 in the paper). The impressive performance indicates the robust generalization ability of our YOSO. 
## usage
```python
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]
```
![Ship](ship_1024.jpg)

## 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}
}
```