ObjectAdd: Adding Objects into Image via a Training-Free Diffusion Modification Fashion

TL;DR

ObjectAdd is a training-free diffusion-based method that enables users to add specific objects into designated areas of an image while maintaining overall image consistency and quality.

Contribution

It introduces a novel training-free approach with technical innovations for precise object insertion and layout control in images generated by diffusion models.

Findings

Successfully adds objects into user-specified areas with high accuracy.

Maintains the rest of the image unchanged after object insertion.

Achieves seamless integration of added objects with the original image.

Abstract

We introduce ObjectAdd, a training-free diffusion modification method to add user-expected objects into user-specified area. The motive of ObjectAdd stems from: first, describing everything in one prompt can be difficult, and second, users often need to add objects into the generated image. To accommodate with real world, our ObjectAdd maintains accurate image consistency after adding objects with technical innovations in: (1) embedding-level concatenation to ensure correct text embedding coalesce; (2) object-driven layout control with latent and attention injection to ensure objects accessing user-specified area; (3) prompted image inpainting in an attention refocusing & object expansion fashion to ensure rest of the image stays the same. With a text-prompted image, our ObjectAdd allows users to specify a box and an object, and achieves: (1) adding object inside the box area; (2) exact content outside the box area; (3) flawless fusion between the two areas