Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model

TL;DR

Diffree is a novel diffusion-based model that enables seamless, text-guided addition of objects into images without requiring bounding boxes or masks, maintaining visual consistency and relevance.

Contribution

We introduce Diffree, a text-guided object addition method trained on a new synthetic dataset, which predicts object placement and integrates objects seamlessly using only text prompts.

Findings

High success rate in object addition

Maintains background and spatial consistency

Outperforms existing methods in relevance and quality

Abstract

This paper addresses an important problem of object addition for images with only text guidance. It is challenging because the new object must be integrated seamlessly into the image with consistent visual context, such as lighting, texture, and spatial location. While existing text-guided image inpainting methods can add objects, they either fail to preserve the background consistency or involve cumbersome human intervention in specifying bounding boxes or user-scribbled masks. To tackle this challenge, we introduce Diffree, a Text-to-Image (T2I) model that facilitates text-guided object addition with only text control. To this end, we curate OABench, an exquisite synthetic dataset by removing objects with advanced image inpainting techniques. OABench comprises 74K real-world tuples of an original image, an inpainted image with the object removed, an object mask, and object descriptions. Trained on OABench using the Stable Diffusion model with an additional mask prediction module, Diffree uniquely predicts the position of the new object and achieves object addition with guidance from only text. Extensive experiments demonstrate that Diffree excels in adding new objects with a high success rate while maintaining background consistency, spatial appropriateness, and object relevance and quality.