Personalized Image Editing in Text-to-Image Diffusion Models via Collaborative Direct Preference Optimization

Input Image User 1: likes black, blue, dislikes pink User 2: likes purple, rainbows, dislikes grey User 3: likes geometric, brown, dislikes black User 4: likes nature, gold, dislikes black User 5: likes blue, neon, futuristic, dislikes pink Figure 1: Our framework performs personalized image editing aligned with user's preference via a novel DPO objective that learns user preferences while leveraging collaborative signals from like-minded individuals.