Skip to yearly menu bar Skip to main content


AnyDoor: Zero-shot Object-level Image Customization

Xi Chen · Lianghua Huang · Yu Liu · Yujun Shen · Deli Zhao · Hengshuang Zhao

Arch 4A-E Poster #175
[ ]
Wed 19 Jun 5 p.m. PDT — 6:30 p.m. PDT


This work presents AnyDoor, a diffusion-based image generator with the power to teleport target objects to new scenes at user-specified locations with desired shapes 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, which are carefully designed to maintain texture details yet allow versatile local variations (e.g., lighting, orientation, posture, etc.), supporting the object in favorably blending with different surroundings. We further propose to borrow knowledge from video datasets, where we can observe various forms (i.e., along the time axis) of a single object, leading to stronger model generalizability and robustness. Extensive experiments demonstrate the superiority of our approach over existing alternatives as well as its great potential in real-world applications, such as virtual try-on and object moving.

Live content is unavailable. Log in and register to view live content