FastFace: Tuning Identity Preservation in Distilled Diffusion via Guidance and Attention
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909626431176704 |
|---|---|
| author | Karpukhin, Sergey Titov, Vadim Kuznetsov, Andrey Alanov, Aibek |
| author_facet | Karpukhin, Sergey Titov, Vadim Kuznetsov, Andrey Alanov, Aibek |
| contents | In latest years plethora of identity-preserving adapters for a personalized generation with diffusion models have been released. Their main disadvantage is that they are dominantly trained jointly with base diffusion models, which suffer from slow multi-step inference. This work aims to tackle the challenge of training-free adaptation of pretrained ID-adapters to diffusion models accelerated via distillation - through careful re-design of classifier-free guidance for few-step stylistic generation and attention manipulation mechanisms in decoupled blocks to improve identity similarity and fidelity, we propose universal FastFace framework. Additionally, we develop a disentangled public evaluation protocol for id-preserving adapters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_21144 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FastFace: Tuning Identity Preservation in Distilled Diffusion via Guidance and Attention Karpukhin, Sergey Titov, Vadim Kuznetsov, Andrey Alanov, Aibek Computer Vision and Pattern Recognition In latest years plethora of identity-preserving adapters for a personalized generation with diffusion models have been released. Their main disadvantage is that they are dominantly trained jointly with base diffusion models, which suffer from slow multi-step inference. This work aims to tackle the challenge of training-free adaptation of pretrained ID-adapters to diffusion models accelerated via distillation - through careful re-design of classifier-free guidance for few-step stylistic generation and attention manipulation mechanisms in decoupled blocks to improve identity similarity and fidelity, we propose universal FastFace framework. Additionally, we develop a disentangled public evaluation protocol for id-preserving adapters. |
| title | FastFace: Tuning Identity Preservation in Distilled Diffusion via Guidance and Attention |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.21144 |