sdxl-turbo-unified-reward-dpo

Model Summary

This model is trained on sdxl-turbo based on DPO preference data constructed by our UnifiedReward-7B for enhanced image generation quality.

For further details, please refer to the following resources:

• 📰 Paper: https://arxiv.org/pdf/2503.05236
• 🪐 Project Page: https://codegoat24.github.io/UnifiedReward/
• 🤗 Model Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-models-67c3008148c3a380d15ac63a
• 🤗 Dataset Collections: https://huggingface.co/collections/CodeGoat24/unifiedreward-training-data-67c300d4fd5eff00fa7f1ede
• 👋 Point of Contact: Yibin Wang

Quick Start

SDXL-Turbo does not make use of guidance_scale or negative_prompt, we disable it with guidance_scale=0.0. Preferably, the model generates images of size 512x512 but higher image sizes work as well. A single step is enough to generate high quality images.

from diffusers import AutoPipelineForText2Image
import torch

pipe = AutoPipelineForText2Image.from_pretrained("CodeGoat24/sdxl-turbo-unified-reward-dpo", torch_dtype=torch.float16, variant="fp16")
pipe.to("cuda")

prompt = "A cinematic shot of a baby racoon wearing an intricate italian priest robe."

image = pipe(prompt=prompt, num_inference_steps=1, guidance_scale=0.0).images[0]

Citation

@article{UnifiedReward,
  title={Unified Reward Model for Multimodal Understanding and Generation.},
  author={Wang, Yibin and Zang, Yuhang, and Li, Hao and Jin, Cheng and Wang Jiaqi},
  journal={arXiv preprint arXiv:2503.05236},
  year={2025}
}