yichaodu commited on
Commit
567b915
1 Parent(s): e52d864

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +11 -5
README.md CHANGED
@@ -3,12 +3,14 @@ tags:
3
  - stable-diffusion
4
  - stable-diffusion-diffusers
5
  - text-to-image
 
 
6
  inference: true
7
  ---
8
 
9
  # Aligned Diffusion Model via DPO
10
 
11
- Diffusion Model Aligned with thef following reward model and DPO algorithm
12
  ```
13
  close-sourced vlm: claude3-opus gemini-1.5 gpt-4o gpt-4v
14
  open-sourced vlm: internvl-1.5
@@ -46,9 +48,13 @@ image = pipeline(prompt=prompt, generator=generator, guidance_scale=gs).images[0
46
 
47
  ## Citation
48
  ```
49
- @misc{mjbench2024mjbench,
50
- title={MJ-BENCH: Is Your Multimodal Reward Model Really a Good Judge?},
51
- author={Chen*, Zhaorun and Du*, Yichao and Wen, Zichen and Zhou, Yiyang and Cui, Chenhang and Weng, Zhenzhen and Tu, Haoqin and Wang, Chaoqi and Tong, Zhengwei and HUANG, Leria and Chen, Canyu and Ye Qinghao and Zhu, Zhihong and Zhang, Yuqing and Zhou, Jiawei and Zhao, Zhuokai and Rafailov, Rafael and Finn, Chelsea and Yao, Huaxiu},
52
- year={2024}
 
 
 
 
53
  }
54
  ```
 
3
  - stable-diffusion
4
  - stable-diffusion-diffusers
5
  - text-to-image
6
+ - DPO
7
+ - DiffusionDPO
8
  inference: true
9
  ---
10
 
11
  # Aligned Diffusion Model via DPO
12
 
13
+ Diffusion model aligned with the following reward models and Direct Preference Optimization (DPO) algorithm
14
  ```
15
  close-sourced vlm: claude3-opus gemini-1.5 gpt-4o gpt-4v
16
  open-sourced vlm: internvl-1.5
 
48
 
49
  ## Citation
50
  ```
51
+ @misc{chen2024mjbenchmultimodalrewardmodel,
52
+ title={MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?},
53
+ 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},
54
+ year={2024},
55
+ eprint={2407.04842},
56
+ archivePrefix={arXiv},
57
+ primaryClass={cs.CV},
58
+ url={https://arxiv.org/abs/2407.04842},
59
  }
60
  ```