Diffusion models have the ability to generate high quality images by denoising pure Gaussian noise images. While previous research has primarily focused on improving the control of image generation through adjusting the denoising process, we propose a novel direction of manipulating the initial noise to control the generated image. Through experiments on stable diffusion, we show that blocks of pixels in the initial latent images have a preference for generating specific content, and that modifying these blocks can significantly influence the generated image. In particular, we show that modifying a part of the initial image affects the corresponding region of the generated image while leaving other regions unaffected, which is useful for repainting tasks. Furthermore, we find that the generation preferences of pixel blocks are primarily determined by their values, rather than their position. By moving pixel blocks with a tendency to generate user-desired content to user-specified regions, our approach achieves state-of-the-art performance in layout-to-image generation. Our results highlight the flexibility and power of initial image manipulation in controlling the generated image. Project Page: https://ut-mao.github.io/swap.github.io/
East China Normal University(华东师范大学);Xiaohongshu Inc.(小红书);KLATASDS, MOE, China(中国教育部统计与数据科学重点实验室);The Chinese University of Hong Kong(香港中文大学);Zhejiang University(浙江大学);Fudan University(复旦大学);University of Oxford(牛津大学);Shanghai Jiao Tong University(上海交通大学);University of Science and Technology of China(中国科学技术大学);Nanjing University(南京大学)
IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment
Zhejiang University(浙江大学);Tencent Youtu Lab(腾讯优图实验室);Shanghai Jiao Tong University(上海交通大学);University of Auckland(奥克兰大学);National University of Singapore(新加坡国立大学)
JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation
Zhejiang University(浙江大学);Tencent Youtu Lab(腾讯优图实验室);Nanjing University(南京大学);University of Auckland(奥克兰大学);Fudan University(复旦大学);National University of Singapore(新加坡国立大学)
Multimodal Image Synthesis and Editing: The Generative AI Era
Max Planck Institute for Informatics(马克斯·普朗克信息研究所);S-Lab, Nanyang Technological University(南洋理工大学S实验室);Nanyang Technological University(南洋理工大学);Carnegie Mellon University(卡内基梅隆大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
RSEdit: Text-Guided Image Editing for Remote Sensing
School of Earth Sciences, Zhejiang University(浙江大学地球科学学院);Zhejiang Provincial Key Laboratory of Geographic Information Science(浙江省地理信息科学重点实验室);Key Laboratory of Spatio-temporal Information and Intelligent Services (LSIIS), Ministry of Natural Resources of the People’s Republic of China(中华人民共和国自然资源部时空信息与智能服务重点实验室);ReLER, CCAI, Zhejiang University(ReLER,中国人工智能学会,浙江大学)
Center for Research on Intelligent Perception and Computing, NLPR, CASIA(中国科学院自动化研究所模式识别国家重点实验室智能感知与计算研究中心);University of Chinese Academy of Sciences(中国科学院大学);Meituandianping Group(美团点评集团);Artificial Intelligence Research, CAS(中国科学院人工智能研究院);Center for Excellence in Brain Science and Intelligence Technology, CAS(中国科学院脑科学与智能技术卓越创新中心)
近年来,人脸肖像编辑技术取得了很大的进步。然而,先前的方法或者1)对预定义的面部属性进行操作,缺乏控制高级语义面部组件的形状的灵活性(例如,眼睛、鼻子、嘴巴),或者2)将手动编辑的遮罩或草图作为可观察变化的中间表示,但是这样的附加输入通常需要额外的努力来获得。为了打破现有方法的局限性(例如形状、遮罩或草图),我们提出了一种新的框架r-FACE(Reference-guided FACE Component Editing),用于进行具有几何变化的多样化和可控的面组件编辑。具体而言,r-FACE以图像修补模型为主干,利用基准图像作为控制面部成分的形状的条件。为了鼓励框架集中在目标人脸组件,一个例子引导的注意力模块被设计为融合注意力特征和目标人脸组件特征提取的参考图像。通过大量的实验验证和比较,我们验证了所提出的框架的有效性。
MADiff: Text-Guided Fashion Image Editing with Mask Prediction and Attention-Enhanced Diffusion
Southeast University(东南大学);Advanced Ocean Institute of Southeast University(东南大学先进海洋研究院);Northwestern Polytechnical University(西北工业大学);Binjiang Institute of Artificial Intelligence, ZJUT(浙江工业大学滨江人工智能研究院);Alibaba Group(阿里巴巴集团)
MotionFollower: Editing Video Motion via Lightweight Score-Guided Diffusion
Fudan University(复旦大学);Shanghai Collaborative Innovation Center of Intelligent Visual Computing(上海智能视觉计算协同创新中心);Microsoft Research Asia(微软亚洲研究院);Carnegie Mellon University(卡内基梅隆大学);Huya Inc.(虎牙公司)