AI Paper Atlas

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

Inpaint-Anywhere: Zero-Shot Multi-Identity Inpainting with Efficient Diffusion Transformer

Junsheng Luan, Lei Zhao, Wei Xing

AAAI 2026 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization · 0 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 filters B and C to filter A (ablation)BoundID dataset · BoundID validationFID: 16.25 -> 8.521Improved
add filter C (aesthetic) on top of A and B (ablation)BoundID dataset · BoundID validationCLIP-I: 0.741 -> 0.823Improved
add filter B on top of filter A (fewer images) (ablation)BoundID dataset · BoundID validationFID: 9.365 -> 16.25 (CLIP-I 0.616 -> 0.741)Mixed
enlarge bounding box by 50% (ablation)Inpaint-Anywhere · BoundID validationFID: 10.04 -> 8.521Improved
enlarge bounding box from 50% to 75% (ablation)Inpaint-Anywhere · BoundID validationDINO / CLIP-T: DINO 0.721 -> 0.703; CLIP-T 0.285 -> 0.261Hurt
use separate IDA and InpA adapters instead of a unified adapter (ablation)Inpaint-Anywhere · BoundID validationFID: 11.57 -> 8.521Improved
add identity adapter IDA (ablation)Inpaint-Anywhere · BoundID validationCLIP-I: 0.616 -> 0.823Improved
add inpainting adapter InpA (ablation)Inpaint-Anywhere · BoundID validationFID: 16.25 -> 8.521Improved
use IMRoPE position shift for identity tokens (ablation)Inpaint-Anywhere · BoundID validationCLIP-I: 0.725 -> 0.823Improved
add position encoder with masked position-aware attention (ablation)Inpaint-Anywhere · BoundID validationidentity-to-region correspondenceImproved
single-pass multi-identity inpainting vs two-pass baselinesInpaint-Anywhere · DreamBenchFID: 8.761 -> 7.619Improved

Earlier methods this paper compares with

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