Views
No views yet
close-sourced vlm: claude3-opus gemini-1.5 gpt-4o gpt-4v
open-sourced vlm: internvl-1.5
score model: hps-2.11from diffusers import StableDiffusionPipeline, UNet2DConditionModel
2
3pretrained_model_name = "runwayml/stable-diffusion-v1-5"
4
5dpo_unet = UNet2DConditionModel.from_pretrained(
6 "path/to/checkpoint",
7 subfolder='unet',
8 torch_dtype=torch.float16
9 ).to('cuda')
10
11pipeline = StableDiffusionPipeline.from_pretrained(pretrained_model_name, torch_dtype=torch.float16)
12pipeline = pipeline.to('cuda')
13pipeline.safety_checker = None
14pipeline.unet = dpo_unet
15
16generator = torch.Generator(device='cuda')
17generator = generator.manual_seed(1)
18
19prompt = "a pink flower"
20
21image = pipeline(prompt=prompt, generator=generator, guidance_scale=gs).images[0]
22@misc{chen2024mjbenchmultimodalrewardmodel,
title={MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?},
author={Zhaorun Chen and Yichao Du and Zichen Wen and Yiyang Zhou and Chenhang Cui and Zhenzhen Weng and Haoqin Tu and Chaoqi Wang and Zhengwei Tong and Qinglan Huang and Canyu Chen and Qinghao Ye and Zhihong Zhu and Yuqing Zhang and Jiawei Zhou and Zhuokai Zhao and Rafael Rafailov and Chelsea Finn and Huaxiu Yao},
year={2024},
eprint={2407.04842},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2407.04842},
}