DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation

TL;DR

DisEnvisioner introduces a tuning-free method that extracts and enriches subject-essential features from a single image, significantly improving personalized image generation by filtering irrelevant information and enhancing ID preservation.

Contribution

It presents a novel disentangled visual prompt approach that effectively separates and enriches subject features for improved customization without tuning.

Findings

Outperforms existing methods in instruction response and ID consistency.

Achieves faster inference and higher image quality.

Demonstrates superior customization performance in experiments.

Abstract

In the realm of image generation, creating customized images from visual prompt with additional textual instruction emerges as a promising endeavor. However, existing methods, both tuning-based and tuning-free, struggle with interpreting the subject-essential attributes from the visual prompt. This leads to subject-irrelevant attributes infiltrating the generation process, ultimately compromising the personalization quality in both editability and ID preservation. In this paper, we present DisEnvisioner, a novel approach for effectively extracting and enriching the subject-essential features while filtering out -irrelevant information, enabling exceptional customization performance, in a tuning-free manner and using only a single image. Specifically, the feature of the subject and other irrelevant components are effectively separated into distinctive visual tokens, enabling a much more accurate customization. Aiming to further improving the ID consistency, we enrich the disentangled features, sculpting them into more granular representations. Experiments demonstrate the superiority of our approach over existing methods in instruction response (editability), ID consistency, inference speed, and the overall image quality, highlighting the effectiveness and efficiency of DisEnvisioner. Project page: https://disenvisioner.github.io/.