AI Paper Atlas

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

WithAnyone: Toward Controllable and ID Consistent Image Generation

Hengyuan Xu, Wei Cheng, Peng Xing, Yixiao Fang, Shuhan Wu, Rui Wang, Xianfang Zeng, Daxin Jiang, Gang YU, Xingjun Ma, Yu-Gang Jiang

ICLR 2026 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization

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 paired-data tuning phase (Phase 3) (ablation)WithAnyone · MultiID-Bench 2-people subsetCopy-Paste (CP): 0.239 -> 0.161Improved
add paired-data tuning phase (Phase 3) (ablation)WithAnyone · MultiID-Bench 2-people subsetSim(GT): 0.406 -> 0.405No clear effect
add GT-aligned ID loss instead of self-aligned landmarks (ablation)WithAnyone · MultiID-Bench 2-people subsetSim(GT): 0.385 -> 0.405Improved
extend negative pool in InfoNCE from 63 in-batch to 4096 (ablation)WithAnyone · MultiID-Bench 2-people subsetSim(GT): 0.368 -> 0.405Improved
add extended negatives in InfoNCE (ablation)WithAnyone · MultiID-Bench 2-people subsetCopy-Paste (CP): 0.074 -> 0.161Hurt
train on MultiID-2M instead of FFHQ only (ablation)WithAnyone · MultiID-Bench 2-people subsetSim(GT): 0.224 -> 0.405Improved
train with MultiID-2M and contrastive/paired training vs prior methodsWithAnyone · MultiID-Bench single-person subsetCopy-Paste (CP) at similar Sim(GT): InstantID 0.464 Sim(GT)/0.337 CP vs Ours 0.460/0.144Improved
use WithAnyone instead of best general models on OmniContextWithAnyone · OmniContext single character subsetOverall: 6.52 vs OmniGen2 8.34Mixed
add paired tuning data (3-4 people)WithAnyone · MultiID-Bench 3-and-4-people subsetSim(GT): 0.379 -> 0.414Improved

Earlier methods this paper compares with

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