Visual Instruction Inversion: Image Editing via Visual Prompting

NeurIPS(2023)

引用 6|浏览37
暂无评分
摘要
Text-conditioned image editing has emerged as a powerful tool for editing images. However, in many situations, language can be ambiguous and ineffective in describing specific image edits. When faced with such challenges, visual prompts can be a more informative and intuitive way to convey ideas. We present a method for image editing via visual prompting. Given pairs of example that represent the "before" and "after" images of an edit, our goal is to learn a text-based editing direction that can be used to perform the same edit on new images. We leverage the rich, pretrained editing capabilities of text-to-image diffusion models by inverting visual prompts into editing instructions. Our results show that with just one example pair, we can achieve competitive results compared to state-of-the-art text-conditioned image editing frameworks.
更多
查看译文
关键词
visual prompting,image editing,instruction,inversion
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要