AI Paper Atlas

Research map / Image generation / Editing and style transfer

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

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

ECCV 2024 · Image generation › Editing and style transfer · approach: Diffusion face generation and editing · 60 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Adapting Area Predictor (background in spatial condition) (ablation)Face-Adapter reenactment · VoxCeleb1 cross-identityFID: 33.61 -> 31.18Improved
add Adapting Area Predictor (ablation)Face-Adapter face swapping · VoxCeleb1FID: 33.97 -> 30.78Improved
add Adapting Area Predictor (ablation)Face-Adapter face swapping · VoxCeleb1ID: 0.4530 -> 0.4688Improved
fine-tune CLIP for attribute features instead of freezing (ablation)Face-Adapter reenactment · VoxCeleb1 cross-identityFID: 33.09 -> 31.18Improved
fine-tune CLIP for attribute features instead of freezing (ablation)Face-Adapter reenactment · VoxCeleb1 cross-identityID (CSIM): 0.6474 -> 0.6616Improved
fine-tune CLIP for attribute features instead of freezing (ablation)Face-Adapter face swapping · VoxCeleb1ID: 0.4696 -> 0.4688No clear effect
add Adapting Area Predictor (ablation)Face-Adapter swapping · VoxCeleb1Pose error: 0.0395 -> 0.0406No clear effect
use Face-Adapter instead of FADM on cross-identity reenactmentreenactment · VoxCeleb1 cross-identityCSIM: 0.6152 -> 0.6429Improved
use landmark-based spatial control from D3DFRFace-Adapter reenactment · VoxCeleb1 same-identityExp error: 2.70 -> 3.24Hurt
use Face-Adapter instead of diffusion DiffSwap for face swappingface swapping · FaceForensics++ID retrieval: 19.16 -> 96.47Improved
use target identity tokens as negative prompt in face swapping inferenceFace-Adapter face swapping · qualitativeidentity similarityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy