SDXS 512 DreamShaper Anime

🚀 SDXS-512-DreamShaper-Anime

SDXS is a real-time high-resolution image generation model based on prompt texts, leveraging score distillation and feature matching techniques. This repository specifically offers an anime-style LoRA for SDXS-512-DreamShaper.

🚀 Quick Start

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

SDXS-512-DreamShaper-Anime is an anime-style LoRA for SDXS-512-DreamShaper. Keep an eye on our repo for any updates.

✨ Features

• Real-time Generation: Generate high-resolution images in real-time based on prompt texts.
• Anime Style: Specifically designed with an anime style for SDXS-512-DreamShaper.

📦 Installation

The installation steps are mainly about setting up the necessary Python environment and dependencies. Ensure you have torch, diffusers, and peft installed. You can use the following command to install the required libraries:

pip install torch diffusers peft

💻 Usage Examples

Basic Usage

The following is a basic example of using SDXS-512-DreamShaper-Anime with the diffusers library:

import torch
from diffusers import StableDiffusionPipeline
import peft

repo = "IDKiro/sdxs-512-dreamshaper"
lora_repo = "IDKiro/sdxs-512-dreamshaper-anime"
weight_type = torch.float16     # or float32

# Load model.
pipe = StableDiffusionPipeline.from_pretrained(repo, torch_dtype=weight_type)
pipe.unet = PeftModel.from_pretrained(pipe.unet, lora_repo)
pipe.to("cuda")

prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"

# Ensure using 1 inference step and CFG set to 0.
image = pipe(
    prompt, 
    num_inference_steps=1, 
    guidance_scale=0
).images[0]

image.save("output.png")

📄 License

The model is licensed under the OpenRAIL++ license.

📚 Documentation

For more detailed information about the model, please refer to our research paper: SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions.

🔧 Technical Details

SDXS is trained using score distillation and feature matching techniques to enable real-time high-resolution image generation. For more technical details, please refer to the research paper.

📚 Cite Our Work

If you use our work in your research, please cite it as follows:

@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},
}