AI Paper Atlas

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

FastComposer: Tuning-Free Multi-subject Image Generation with Localized Attention

Guangxuan Xiao, Tianwei Yin, William T. Freeman, Frédo Durand, Song Han

IJCV 2024 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization · 299 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 cross-attention localization loss (ablation)FastComposer · Multi-subject generationidentity preservation: 37.66% -> 43.11%Improved
add cross-attention localization loss (ablation)FastComposer · Multi-subject generationprompt consistency: 25.03% -> 24.25%Hurt
raise ratio of timesteps with subject conditioning (ablation)FastComposer delayed conditioning · Single-subjectidentity vs editabilityMixed
replace per-subject fine-tuning with tuning-free subject embeddingFastComposer vs Custom Diffusion · Single-subjectidentity preservation: 43.37% -> 51.41%Improved
replace fine-tuning with tuning-free subject embeddingFastComposer vs Custom Diffusion · Multi-subjectidentity preservation: 5.37% -> 43.11%Improved
replace fine-tuning with tuning-free subject embeddingFastComposer vs Textual-Inversion · Single-subjecttotal time: 2500 s -> 2 sImproved

Later papers that compared with this method

16 later accepted papers report FastComposer as a baseline in their results tables; 13 of them report a better number on most of the results they share with it.

8 more not listed.

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