Instruction-based Image Manipulation by Watching How Things Move

2 Adobe Change the view to the side Lower the horse's head Make the man look angry Close the dog's eyes Have the man look at the side Move the camera to the left

Figure 1. We propose InstructMove, an instruction-based image editing model trained on frame pairs from videos with instructions generated by Multimodal LLMs. Our model excels at non-rigid editing, such as adjusting subject poses, expressions, and altering viewpoints, while maintaining content consistency. Additionally, our method supports precise, localized edits through the integration of masks, human poses, and other control mechanisms.