no code implementations • 5 Jun 2024 • Yuanhao Ban, Ruochen Wang, Tianyi Zhou, Minhao Cheng, Boqing Gong, Cho-Jui Hsieh
The concept of negative prompts, emerging from conditional generation models like Stable Diffusion, allows users to specify what to exclude from the generated images.%, demonstrating significant practical efficacy.
no code implementations • 4 Jun 2024 • Yuanhao Ban, Ruochen Wang, Tianyi Zhou, Boqing Gong, Cho-Jui Hsieh, Minhao Cheng
We identify these patches by analyzing the dispersion of object bounding boxes across generated images, leading to the development of a posterior analysis technique.
1 code implementation • 7 Oct 2022 • Yuanhao Ban, Yinpeng Dong
Self-supervised pre-training has drawn increasing attention in recent years due to its superior performance on numerous downstream tasks after fine-tuning.