Training-Free Sketch-Guided Diffusion with Latent Optimization

TL;DR

This paper introduces a training-free, sketch-guided image generation method that uses latent optimization and cross-attention maps to produce images closely aligned with user sketches, enhancing control and customization.

Contribution

It presents a novel training-free pipeline that incorporates sketch guidance into diffusion models via latent optimization and cross-attention maps, improving image structure fidelity.

Findings

Enhanced image accuracy with sketch guidance

Training-free approach simplifies integration

Latent optimization refines structure adherence

Abstract

Based on recent advanced diffusion models, Text-to-image (T2I) generation models have demonstrated their capabilities to generate diverse and high-quality images. However, leveraging their potential for real-world content creation, particularly in providing users with precise control over the image generation result, poses a significant challenge. In this paper, we propose an innovative training-free pipeline that extends existing text-to-image generation models to incorporate a sketch as an additional condition. To generate new images with a layout and structure closely resembling the input sketch, we find that these core features of a sketch can be tracked with the cross-attention maps of diffusion models. We introduce latent optimization, a method that refines the noisy latent at each intermediate step of the generation process using cross-attention maps to ensure that the generated images adhere closely to the desired structure outlined in the reference sketch. Through latent optimization, our method enhances the accuracy of image generation, offering users greater control and customization options in content creation.