AI Paper Atlas

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

MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation

Kunpeng Song, Yizhe Zhu, Bingchen Liu, Qing Yan, Ahmed Elgammal, Xiao Yang

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization · 39 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 iterative self-attention masking (strength 1.0) in subject-cross-attention (ablation)MoMA · DreamBooth datasetCLIP-T (recontextualization): 0.298 -> 0.348Improved
add iterative self-attention masking (strength 1.0) in subject-cross-attention (ablation)MoMA · DreamBooth datasetDINO: 0.575 -> 0.618Improved
add self-attention masking for texture editing (ablation)MoMA · DreamBooth datasetCLIP-T (texture editing): 0.322 (w/o) -> 0.335 (full), 0.231 at half strengthMixed
add subject-cross-attention self-attention feature transfer (beta=1.0) (ablation)MoMA · DreamBooth datasetDINO: 0.583 -> 0.618Improved
add subject-cross-attention feature transfer (ablation)MoMA · DreamBooth datasetCLIP-I: 0.782 -> 0.803Improved
increase subject-cross-attention strength beta from 0.5 to 1.0 (ablation)MoMA · DreamBooth datasetCLIP-T (recontextualization): 0.348 -> 0.348No clear effect
increase subject-cross-attention strength beta from 0.5 to 1.0 for texture editing (ablation)MoMA · DreamBooth datasetCLIP-T (texture editing): 0.338 -> 0.335Hurt
use MoMA multimodal LLM decoder with contextualized features instead of IP-AdapterIP-Adapter · DreamBooth datasetCLIP-T (texture editing): 0.319 -> 0.335Improved
use MoMA instead of IP-Adapter in human evaluationIP-Adapter · Human evaluationPrompt Fidelity: 0.351 -> 0.633Improved

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