Persistent Identity Preservation in Generative Image Models: A Benchmark and Evaluation System

The paper introduces a benchmark and evaluation system for measuring how well generative image models preserve the identity of a subject across generation, editing, restoration, and multi‑subject scenarios. It compares three paradigms—input context, trainable subject‑specific parameters, and a persistent identity layer—showing that persistent identity consistently improves fidelity while keeping image quality and instruction adherence high. The study finds that identity preservation remains a distinct limitation of current foundation models, especially under iterative edits, small scales, severe degradation, and multi‑subject composition.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• llms
• fine-tuning
• benchmarks