Views
No views yet
close-sourced vlm: claude3-opus gpt-4o gpt-4v1from diffusers import StableDiffusionPipeline, UNet2DConditionModel
2
3pretrained_model_name = "runwayml/stable-diffusion-v1-5"
4pipeline = StableDiffusionPipeline.from_pretrained(pretrained_model_name, torch_dtype=torch.float16)
5
6lora_path = os.path.join(""path/to/checkpoint"")
7pipeline.sd_pipeline.load_lora_weights(lora_path)
8pipeline.sd_pipeline.to("cuda")
9
10generator = torch.Generator(device='cuda')
11generator = generator.manual_seed(1)
12
13prompt = "a pink flower"
14
15image = pipeline(prompt=prompt, generator=generator, guidance_scale=5).images[0]@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},
}