Score: 0

Training-Free Identity Preservation in Stylized Image Generation Using Diffusion Models

Published: June 7, 2025 | arXiv ID: 2506.06802v1

By: Mohammad Ali Rezaei , Helia Hajikazem , Saeed Khanehgir and more

Potential Business Impact:

Keeps faces the same when changing picture styles.

Business Areas:
Identity Management Information Technology, Privacy and Security

While diffusion models have demonstrated remarkable generative capabilities, existing style transfer techniques often struggle to maintain identity while achieving high-quality stylization. This limitation is particularly acute for images where faces are small or exhibit significant camera-to-face distances, frequently leading to inadequate identity preservation. To address this, we introduce a novel, training-free framework for identity-preserved stylized image synthesis using diffusion models. Key contributions include: (1) the "Mosaic Restored Content Image" technique, significantly enhancing identity retention, especially in complex scenes; and (2) a training-free content consistency loss that enhances the preservation of fine-grained content details by directing more attention to the original image during stylization. Our experiments reveal that the proposed approach substantially surpasses the baseline model in concurrently maintaining high stylistic fidelity and robust identity integrity, particularly under conditions of small facial regions or significant camera-to-face distances, all without necessitating model retraining or fine-tuning.

Country of Origin
🇮🇷 Iran

Page Count
11 pages

Category
Computer Science:
CV and Pattern Recognition