README.md

---
license: openrail++
tags:
- text-to-image
- stable-diffusion
library_name: diffusers
inference: false
---

# SDXS-512-0.9

SDXS is a model that can generate high-resolution images in real-time based on prompt texts, trained using score distillation and feature matching. For more information, please refer to our research paper: SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions. We open-source the model as part of the research.

SDXS-512-0.9 is a **old version** of SDXS-512. For some reasons, we are only releasing this version for the time being, and will gradually release other versions.

Model Information:
- Teacher DM: [SD Turbo](https://huggingface.co/stabilityai/sd-turbo)
- Offline DM: [SD v2.1 base](https://huggingface.co/stabilityai/stable-diffusion-2-1-base)
- VAE: [TAESD](https://huggingface.co/madebyollin/taesd)

Note that TAESD may produce low-quality images when weight_type is float16. Our image decoder is not compatible with the current version of diffusers, so it will not be provided now.

## Diffusers Usage

![](output.png)

```python
import torch
from diffusers import StableDiffusionPipeline, AutoencoderKL

repo = "IDKiro/sdxs-512-0.9"
seed = 42
weight_type = torch.float32     # or float16

# Load model.
pipe = StableDiffusionPipeline.from_pretrained(repo, torch_dtype=weight_type)
# pipe.vae = AutoencoderKL.from_pretrained("IDKiro/sdxs-512-0.9/vae_large")     # use original VAE
pipe.to("cuda")

prompt = "portrait photo of a girl, photograph, highly detailed face, depth of field, moody light, golden hour"

# Ensure using the same inference steps as the loaded model and CFG set to 0.
image = pipe(
    prompt, 
    num_inference_steps=1, 
    guidance_scale=0,
    generator=torch.Generator(device="cuda").manual_seed(seed)
).images[0]

image.save("output.png")
```

## Cite Our Work

```
@article{song2024sdxs,
  author    = {Yuda Song, Zehao Sun, Xuanwu Yin},
  title     = {SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions},
  journal   = {arxiv},
  year      = {2024},
}
```