AnyDoor: Zero-shot Object-level Image Customization

arXiv:2307.09481v2 Announce Type: replace
Abstract: This work presents AnyDoor, a diffusion-based image generator with the power to teleport target objects to new scenes at user-specified locations in a harmonious way. Instead of tuning parameters for each object, our model is trained only once and effortlessly generalizes to diverse object-scene combinations at the inference stage. Such a challenging zero-shot setting requires an adequate characterization of a certain object. To this end, we complement the commonly used identity feature with detail features, …

arxiv cs.cv customization image object type zero-shot