Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control

About

Current face reenactment and swapping methods mainly rely on GAN frameworks, but recent focus has shifted to pre-trained diffusion models for their superior generation capabilities. However, training these models is resource-intensive, and the results have not yet achieved satisfactory performance levels. To address this issue, we introduce Face-Adapter, an efficient and effective adapter designed for high-precision and high-fidelity face editing for pre-trained diffusion models. We observe that both face reenactment/swapping tasks essentially involve combinations of target structure, ID and attribute. We aim to sufficiently decouple the control of these factors to achieve both tasks in one model. Specifically, our method contains: 1) A Spatial Condition Generator that provides precise landmarks and background; 2) A Plug-and-play Identity Encoder that transfers face embeddings to the text space by a transformer decoder. 3) An Attribute Controller that integrates spatial conditions and detailed attributes. Face-Adapter achieves comparable or even superior performance in terms of motion control precision, ID retention capability, and generation quality compared to fully fine-tuned face reenactment/swapping models. Additionally, Face-Adapter seamlessly integrates with various StableDiffusion models.

Yue Han, Junwei Zhu, Keke He, Xu Chen, Yanhao Ge, Wei Li, Xiangtai Li, Jiangning Zhang, Chengjie Wang, Yong Liu• 2024

Related benchmarks

TaskDatasetResultRank
Face SwappingFFHQ
FID13.03
35
Portrait Animation (Self-reenactment)VFHQ (test)
FVD472.3
23
Dual Face-Hair RetrievalDFHR-Bench Bimodal Alignment
Recall@110.63
19
Face SwappingFFHQ (test)
FID13.03
13
Image-Text RetrievalDFHR-Bench (Official Set)
Recall@111.46
11
Image+Text Dual Face-Hair RetrievalDFHR-Bench Image+Text official set
R@111.46
11
Facial ReconstructionUser Study
ID Consistency3.61
10
Identity-Preserving Image EditingReal-world scenarios (test)
ID-Sim0.4
10
Face SwappingFF++
ID Similarity0.247
10
Head Swappingcollected 30 pairs (test)
CSIM0.533
8
Showing 10 of 21 rows

Other info

Follow for update