AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

MasterWeaver: Taming Editability and Face Identity for Personalized Text-to-Image Generation

Yuxiang Wei, Zhilong Ji, Jinfeng Bai, Hongzhi Zhang, Lei Zhang, Wangmeng Zuo

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization · 14 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 editing direction loss L_edit (ablation)MasterWeaver · CelebA-HQ single referenceCLIP-T: 0.209 -> 0.232Improved
add editing direction loss L_edit (ablation)MasterWeaver · CelebA-HQ single referenceFace similarity: 0.637 -> 0.631Hurt
add background disentanglement loss L_disen (ablation)MasterWeaver · CelebA-HQ single referenceCLIP-T: 0.226 -> 0.232Improved
add background disentanglement loss L_disen (ablation)MasterWeaver · CelebA-HQ single referenceFace similarity: 0.617 -> 0.631Improved
add face-augmented dataset (ablation)MasterWeaver · CelebA-HQ single referenceCLIP-T: 0.221 -> 0.232Improved
add face-augmented dataset (ablation)MasterWeaver · CelebA-HQ single referenceFace similarity: 0.634 -> 0.631No clear effect
apply L_edit to more up blocks (Upblock1+2+3) (ablation)MasterWeaver · CelebA-HQ single referenceFace similarity: 0.631 -> 0.568Hurt
increase lambda in identity cross attention (ablation)MasterWeaver · CelebA-HQ single referenceidentity metrics vs CLIP-TMixed
use MasterWeaver instead of FastComposer/IP-Adaptersingle-reference personalization · CelebA-HQ single referenceCLIP-T: 0.201 -> 0.232 (vs FastComposer)Improved
add more reference images at inference by concatenating identity tokensMasterWeaver · multi-referenceidentity fidelityImproved

Later papers that compared with this method

1 later accepted paper reports MasterWeaver as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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