DDPO-alignment-claude3-opus

Aligned Diffusion Model via DDPO

Diffusion model aligned with the following reward models and Denoising Diffusion Policy Optimization (DDPO) algorithm

close-sourced vlm: claude3-opus  gpt-4o  gpt-4v

How to Use

You can load the model and perform inference as follows:

from diffusers import StableDiffusionPipeline, UNet2DConditionModel

pretrained_model_name = "runwayml/stable-diffusion-v1-5"
pipeline = StableDiffusionPipeline.from_pretrained(pretrained_model_name, torch_dtype=torch.float16)

lora_path = os.path.join(""path/to/checkpoint"")
pipeline.sd_pipeline.load_lora_weights(lora_path)
pipeline.sd_pipeline.to("cuda")

generator = torch.Generator(device='cuda')
generator = generator.manual_seed(1)

prompt = "a pink flower"

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}, 
}