FlexID: Training-Free Flexible Identity Injection via Intent-Aware Modulation for Text-to-Image Generation

TL;DR

FlexID is a training-free framework for personalized text-to-image generation that dynamically balances identity fidelity and textual adaptability using intent-aware modulation.

Contribution

It introduces a novel intent-aware modulation method that decouples identity into semantic and visual components, enabling flexible identity injection without training.

Findings

Achieves state-of-the-art balance between identity preservation and text adherence.

Effectively relaxes visual constraints based on editing intent.

Demonstrates superior performance on IBench dataset.

Abstract

Personalized text-to-image generation aims to seamlessly integrate specific identities into textual descriptions. However, existing training-free methods often rely on rigid visual feature injection, creating a conflict between identity fidelity and textual adaptability. To address this, we propose FlexID, a novel training-free framework utilizing intent-aware modulation. FlexID orthogonally decouples identity into two dimensions: a Semantic Identity Projector (SIP) that injects high-level priors into the language space, and a Visual Feature Anchor (VFA) that ensures structural fidelity within the latent space. Crucially, we introduce a Context-Aware Adaptive Gating (CAG) mechanism that dynamically modulates the weights of these streams based on editing intent and diffusion timesteps. By automatically relaxing rigid visual constraints when strong editing intent is detected, CAG achieves synergy between identity preservation and semantic variation. Extensive experiments on IBench demonstrate that FlexID achieves a state-of-the-art balance between identity consistency and text adherence, offering an efficient solution for complex narrative generation.