Views
No views yet
1import torch
2from diffusers import StableDiffusionPipeline, UNet2DConditionModel
3
4unet = UNet2DConditionModel.from_pretrained(
5 "ylwu/diffusion-dro-sd1.5",
6 subfolder="unet",
7 torch_dtype=torch.bfloat16
8).to('cuda')
9
10pipe = StableDiffusionPipeline.from_pretrained(
11 "stable-diffusion-v1-5/stable-diffusion-v1-5",
12 unet=unet,
13 torch_dtype=torch.bfloat16
14).to('cuda')
15
16prompt = "A new artwork depicting Pikachu as a superhero fighting villains with dramatic lightning"
17image = pipe(prompt).images[0]
18image.save("example.png")@misc{wu2025rankingbasedpreferenceoptimizationdiffusion,
title={Ranking-based Preference Optimization for Diffusion Models from Implicit User Feedback},
author={Yi-Lun Wu and Bo-Kai Ruan and Chiang Tseng and Hong-Han Shuai},
year={2025},
eprint={2510.18353},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2510.18353},
}