ECNet: Effective Controllable Text-to-Image Diffusion Models

TL;DR

ECNet introduces innovative guidance and supervision techniques to significantly improve the controllability and robustness of text-to-image diffusion models, enabling more precise and reliable image generation from complex conditions.

Contribution

The paper presents Spatial Guidance Injector and Diffusion Consistency Loss, novel methods that enhance control accuracy and supervision in diffusion-based text-to-image models.

Findings

Enhanced controllability over various conditions

Outperforms existing state-of-the-art models

Improved robustness and precision in image generation

Abstract

The conditional text-to-image diffusion models have garnered significant attention in recent years. However, the precision of these models is often compromised mainly for two reasons, ambiguous condition input and inadequate condition guidance over single denoising loss. To address the challenges, we introduce two innovative solutions. Firstly, we propose a Spatial Guidance Injector (SGI) which enhances conditional detail by encoding text inputs with precise annotation information. This method directly tackles the issue of ambiguous control inputs by providing clear, annotated guidance to the model. Secondly, to overcome the issue of limited conditional supervision, we introduce Diffusion Consistency Loss (DCL), which applies supervision on the denoised latent code at any given time step. This encourages consistency between the latent code at each time step and the input signal, thereby enhancing the robustness and accuracy of the output. The combination of SGI and DCL results in our Effective Controllable Network (ECNet), which offers a more accurate controllable end-to-end text-to-image generation framework with a more precise conditioning input and stronger controllable supervision. We validate our approach through extensive experiments on generation under various conditions, such as human body skeletons, facial landmarks, and sketches of general objects. The results consistently demonstrate that our method significantly enhances the controllability and robustness of the generated images, outperforming existing state-of-the-art controllable text-to-image models.