FlashFace: Human Image Personalization with High-fidelity Identity Preservation

TL;DR

FlashFace is a practical tool enabling high-fidelity human image personalization by preserving detailed identity features and effectively integrating text prompts, outperforming existing methods in quality and instruction adherence.

Contribution

The paper introduces a novel face encoding and a disentangled guidance strategy that significantly improve identity preservation and instruction following in text-to-image personalization.

Findings

Achieves superior identity preservation with detailed facial features.

Effectively balances text and image guidance during generation.

Demonstrates versatility across various human image personalization tasks.

Abstract

This work presents FlashFace, a practical tool with which users can easily personalize their own photos on the fly by providing one or a few reference face images and a text prompt. Our approach is distinguishable from existing human photo customization methods by higher-fidelity identity preservation and better instruction following, benefiting from two subtle designs. First, we encode the face identity into a series of feature maps instead of one image token as in prior arts, allowing the model to retain more details of the reference faces (e.g., scars, tattoos, and face shape ). Second, we introduce a disentangled integration strategy to balance the text and image guidance during the text-to-image generation process, alleviating the conflict between the reference faces and the text prompts (e.g., personalizing an adult into a "child" or an "elder"). Extensive experimental results demonstrate the effectiveness of our method on various applications, including human image personalization, face swapping under language prompts, making virtual characters into real people, etc. Project Page: https://jshilong.github.io/flashface-page.