Upload README.md with huggingface_hub

README.md

@@ -9,7 +9,7 @@ inference: true
 
 # Aligned Diffusion Model via DDPO
 
-Diffusion Model aligned with the following reward models and Denoising Diffusion Policy Optimization (DDPO) algorithm
+Diffusion model aligned with the following reward models and Denoising Diffusion Policy Optimization (DDPO) algorithm
 ```
 close-sourced vlm: claude3-opus  gpt-4o  gpt-4v
 ```
@@ -38,12 +38,12 @@ image = pipeline(prompt=prompt, generator=generator, guidance_scale=5).images[0]
 ## Citation
 ```
 @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}, 
+    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}, 
 }
 ```