Stable-Hair: Real-World Hair Transfer via Diffusion Model
Open Access
- 11 April 2025
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (10) , 10348-10356
Abstract
Current hair transfer methods struggle to handle diverse and intricate hairstyles, limiting their applicability in real-world scenarios. In this paper, we propose a novel diffusion-based hair transfer framework, named Stable-Hair, which robustly transfers a wide range of real-world hairstyles to user-provided faces for virtual hair try-on. To achieve this goal, our Stable-Hair framework is designed as a two-stage pipeline. In the first stage, we train a Bald Converter alongside stable diffusion to remove hair from the user-provided face images, resulting in bald images. In the second stage, we specifically designed a Hair Extractor and a Latent IdentityNet to transfer the target hairstyle with highly detailed and high-fidelity to the bald image. The Hair Extractor is trained to encode reference images with the desired hairstyles, while the Latent IdentityNet ensures consistency in identity and background. To minimize color deviations between source images and transfer results, we introduce a novel Latent ControlNet architecture, which functions as both the Bald Converter and Latent IdentityNet. After training on our curated triplet dataset, our method accurately transfers highly detailed and high-fidelity hairstyles to the source images. Extensive experiments demonstrate that our approach achieves state-of-the-art performance compared to existing hair transfer methods.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- iEdit: Localised Text-guided Image Editing with Weak Supervision2024
- Stable VITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On2024
- HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models2024
- MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing2023
- Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion ModelsACM Transactions on Graphics, 2023
- DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation2023
- GAN with Multivariate Disentangling for Controllable Hair Editing2022
- Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment2022
- ArcFace: Additive Angular Margin Loss for Deep Face RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004