Grounding Text-to-Image Diffusion Models for Controlled High-Quality Image Generation

TL;DR

ObjectDiffusion is a novel model that enhances text-to-image diffusion by integrating semantic and spatial grounding, enabling precise control over object placement and improving image quality and diversity.

Contribution

The paper introduces ObjectDiffusion, a new approach that conditions diffusion models on grounding information, combining ControlNet and GLIGEN techniques for improved controllable image synthesis.

Findings

Achieves state-of-the-art metrics on COCO2017 dataset

Demonstrates strong grounding and control in diverse contexts

Produces high-fidelity images with precise object placement

Abstract

Text-to-image (T2I) generative diffusion models have demonstrated outstanding performance in synthesizing diverse, high-quality visuals from text captions. Several layout-to-image models have been developed to control the generation process by utilizing a wide range of layouts, such as segmentation maps, edges, and human keypoints. In this work, we propose ObjectDiffusion, a model that conditions T2I diffusion models on semantic and spatial grounding information, enabling the precise rendering and placement of desired objects in specific locations defined by bounding boxes. To achieve this, we make substantial modifications to the network architecture introduced in ControlNet to integrate it with the grounding method proposed in GLIGEN. We fine-tune ObjectDiffusion on the COCO2017 training dataset and evaluate it on the COCO2017 validation dataset. Our model improves the precision and quality of controllable image generation, achieving an AP$_{\text{50}}$ of 46.6, an AR of 44.5, and an FID of 19.8, outperforming the current SOTA model trained on open-source datasets across all three metrics. ObjectDiffusion demonstrates a distinctive capability in synthesizing diverse, high-quality, high-fidelity images that seamlessly conform to the semantic and spatial control layout. Evaluated in qualitative and quantitative tests, ObjectDiffusion exhibits remarkable grounding capabilities in closed-set and open-set vocabulary settings across a wide variety of contexts. The qualitative assessment verifies the ability of ObjectDiffusion to generate multiple detailed objects in varying sizes, forms, and locations.