---
language:
- en
pipeline_tag: text-to-image
library_name: diffusers
tags:
- lora
---
# 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).

## Note
**This is our old-version LoRA**. We have re-trained the YOSO-LoRA via more computational resources and better data, achieving better one-step performance. Check the [technical report](https://www.arxiv.org/abs/2403.12931) for more details! The newly trained LoRA may be released in the next few months.



## Usage

### 1-step inference
1-step inference is only allowed based on SD v1.5 for now. And you should prepare the informative initialization according to the paper for better results.
```python
import torch
from diffusers import DiffusionPipeline, LCMScheduler
pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype = torch.float16)
pipeline = pipeline.to('cuda')
pipeline.scheduler = LCMScheduler.from_config(pipeline.scheduler.config)
pipeline.load_lora_weights('Luo-Yihong/yoso_sd1.5_lora')
generator = torch.manual_seed(318)
steps = 1
bs = 1
latents = ... # maybe some latent codes of real images or SD generation
latent_mean = latent.mean(dim=0)
init_latent = latent_mean.repeat(bs,1,1,1) + latents.std()*torch.randn_like(latents) 
noise = torch.randn([bs,4,64,64])
input_latent = pipeline.scheduler.add_noise(init_latent,noise,T)
imgs= pipeline(prompt="A photo of a dog",
                    num_inference_steps=steps, 
                    num_images_per_prompt = 1,
                        generator = generator,
                        guidance_scale=1.5,
                    latents = input_latent,
                   )[0]
imgs
```

The simple inference without informative initialization, but worse quality:
```python
pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype = torch.float16)
pipeline = pipeline.to('cuda')
pipeline.scheduler = LCMScheduler.from_config(pipeline.scheduler.config)
pipeline.load_lora_weights('Luo-Yihong/yoso_sd1.5_lora')
generator = torch.manual_seed(318)
steps = 1
imgs = pipeline(prompt="A photo of a corgi in forest, highly detailed, 8k, XT3.",
                    num_inference_steps=1, 
                    num_images_per_prompt = 1,
                        generator = generator,
                        guidance_scale=1.,
                   )[0]
imgs[0]
```
![Corgi](corgi.jpg)
### 2-step inference
We note that a small CFG can be used to enhance the image quality.
```python
pipeline = DiffusionPipeline.from_pretrained("stablediffusionapi/realistic-vision-v51", torch_dtype = torch.float16)
pipeline = pipeline.to('cuda')
pipeline.scheduler = LCMScheduler.from_config(pipeline.scheduler.config)
pipeline.load_lora_weights('Luo-Yihong/yoso_sd1.5_lora')
generator = torch.manual_seed(318)
steps = 2
imgs= pipeline(prompt="A photo of a man, XT3",
                    num_inference_steps=steps, 
                    num_images_per_prompt = 1,
                        generator = generator,
                        guidance_scale=1.5,
                   )[0]
imgs
```
![man](man.jpg)

Moreover, it is observed that when combined with new base models, our YOSO-LoRA is able to use some advanced ode-solvers:
```python
import torch
from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
pipeline = DiffusionPipeline.from_pretrained("stablediffusionapi/realistic-vision-v51", torch_dtype = torch.float16)
pipeline = pipeline.to('cuda')
pipeline.load_lora_weights('Luo-Yihong/yoso_sd1.5_lora')
pipeline.scheduler = DPMSolverMultistepScheduler.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="scheduler")
generator = torch.manual_seed(323)
steps = 2
imgs= pipeline(prompt="A photo of a girl, XT3",
                    num_inference_steps=steps, 
                    num_images_per_prompt = 1,
                        generator = generator,
                        guidance_scale=1.5,
                   )[0]
imgs[0]
```
![girl](girl.jpg)

We encourage you to experiment with various solvers to obtain better samples. We will try to improve the compatibility of the YOSO-LoRA with different solvers.

You may try some interesting applications, like:
```python
generator = torch.manual_seed(318)
steps = 2
img_list = []
for age in [2,20,30,50,60,80]:
    imgs = pipeline(prompt=f"A photo of a cute girl, {age} yr old, XT3",
                        num_inference_steps=steps, 
                        num_images_per_prompt = 1,
                            generator = generator,
                            guidance_scale=1.1,
                       )[0]
    img_list.append(imgs[0])
make_image_grid(img_list,rows=1,cols=len(img_list))
```
![life](life.jpg)

You can increase the steps to improve sample quality.

## 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}
}
```