Recent advancements in instruction-based image editing and subject-driven generation have garnered significant attention, yet both tasks still face limitations in meeting practical user needs. Instruction-based editing relies solely on language instructions, which often fail to capture specific editing details, making reference images necessary. Meanwhile, subject-driven generation is limited to combining concrete objects or people, overlooking broader, abstract concepts. To address these challenges, we propose two novel tasks: multimodal instruction-based editing and generation. These tasks support both text and image instructions and extend the scope to include both concrete and abstract concepts, greatly enhancing their practical applications. We introduce DreamOmni2, tackling two primary challenges: data creation and model framework design. Our data synthesis pipeline consists of three steps: (1) using a feature mixing method to create extraction data for both abstract and concrete concepts, (2) generating multimodal instruction-based editing training data using the editing and extraction models, and (3) further applying the extraction model to create training data for multimodal instruction-based editing. For the framework, to handle multi-image input, we propose an index encoding and position encoding shift scheme, which helps the model distinguish images and avoid pixel confusion. Additionally, we introduce joint training with the VLM and our generation/editing model to better process complex instructions. In addition, we have proposed comprehensive benchmarks for these two new tasks to drive their development. Experiments show that DreamOmni2 has achieved impressive results. Models and codes will be released.
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）
Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions
Department of Electronic Engineering and Computer Science University of California, Irvine（电子工程与计算机科学系 加州大学尔湾分校）；Department of Computer Science University of Alabama at Birmingham（计算机科学系 阿拉巴马大学伯明翰分校）
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）
MIGE: Mutually Enhanced Multimodal Instruction-Based Image Generation and Editing
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences（人工智能安全国家重点实验室，计算技术研究所，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）
SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models
University of Macau（澳门大学）；ARC Lab, Tencent PCG（腾讯平台与内容事业群ARC实验室）；Tencent AI Lab（腾讯人工智能实验室）；Shenzhen Institute of Advanced Technology（深圳先进技术研究院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Tsinghua University（清华大学）
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）
RefVideo-6M: A Reliable Reference-Based Dataset for Instructional Video Editing
Institute of Artificial Intelligence, China Telecom (TeleAI)（中国电信人工智能研究院（TeleAI））；The Chinese University of Hong Kong (CUHK)（香港中文大学）；Sun Yat-sen University（中山大学）；Fudan University（复旦大学）；Tsinghua University（清华大学）
How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing
School of Artificial Intelligence, University of Chinese Academy of Science（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Language Technology Lab, University of Cambridge（剑桥大学语言技术实验室）；Peking University（北京大学）；South China University of Technology（华南理工大学）；Nanjing University（南京大学）
Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning
Tencent Youtu Lab（腾讯云图实验室）；Sichuan University（四川大学）；University of the Chinese Academy of Sciences（中国科学院大学）；Fudan University（复旦大学）；Zhejiang University（浙江大学）；National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）
