Latent-Identity Tuning in Text-to-Image Personalization Models

Research area: Computer Vision Authors: Daniel Garibi, Ronen Kamenetsky, Hadar Averbuch-Elor, Daniel Cohen-Or, Or Patashnik Published: 2026-07-13 arXiv: 2607.11885

Summary

Generating and editing a person's face demands high precision, as even minor modifications can significantly alter a subject's perceived identity. Current personalization and editing methods built on general-purpose text-to-image models, however, often lack the precision required for fine-grained facial edits.

This paper presents a method for fine-grained identity tuning in text-to-image personalization models. Unlike standard image editing, which operates on a given image, identity tuning modifies the latent representation of a specific identity, enabling the generation of diverse images that consistently depict the same edited identity.

To enable fine-grained latent identity tuning, the authors explore the latent space of a pre-trained, frozen encoder for text-to-image personalization, leveraging its existing architecture to discover latent semantic directions. This space consists of a set of latent tokens that capture different aspects of identity, often corresponding to specific spatial or semantic facial regions. The study shows that meaningful directions can be identified within this space — and within subspaces defined by selected tokens — enabling localized, fine-grained, and semantically consistent edits.

Qualitative and quantitative experiments validate the method's ability to perform diverse localized facial edits while preserving identity consistency across generated images.

Full Abstract

Generating and editing a person's face demands high precision, as even minor modifications can significantly alter a subject's perceived identity. Current personalization and editing methods built on general-purpose text-to-image models, however, often lack the precision required for fine-grained facial edits. We present a method for fine-grained identity tuning in text-to-image personalization models. Unlike standard image editing, which operates on a given image, identity tuning modifies the latent representation of a specific identity, enabling the generation of diverse images that consistently depict the same edited identity. To enable fine-grained latent identity tuning, we explore the latent space of a pre-trained, frozen encoder for text-to-image personalization. Our approach requires... *(excerpt truncated in source post)*

---

*Auto-collected on 2026-07-15*