AI Paper Atlas

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

OmniPortrait: Fine-Grained Personalized Portrait Synthesis via Pivotal Optimization

Dongxu Yue, Bo Lin, Yao Tang, Jiajun Liang, Zhihai He, Chun Yuan

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 face localization loss to Pivot ID Encoder training (ablation)OmniPortrait · Ablation (SDXL, 50 IDs)SIM: 35.01 -> 69.13Improved
add face localization loss to Pivot ID Encoder training (ablation)OmniPortrait · Ablation (SDXL, 50 IDs)FID: 476.22 -> 213.48Improved
add Pivot ID Encoder (ablation)OmniPortrait · Ablation (SDXL, 50 IDs)SIM: 14.15 -> 69.13Improved
add Pivot ID Encoder (ablation)OmniPortrait · Ablation (SDXL, 50 IDs)CLIP-I: 21.83 -> 73.08Improved
add background gradient masking (ablation)OmniPortrait · Ablation (SDXL, 50 IDs)SIM: 33.42 -> 69.13Improved
add background gradient masking (ablation)OmniPortrait · Ablation (SDXL, 50 IDs)CLIP-T: 19.34 -> 24.25Improved
add RB-Guidance (ablation)OmniPortrait · Ablation (SDXL, 50 IDs)SIM: 63.87 -> 69.13Improved
add RB-Guidance (ablation)OmniPortrait · Ablation (SDXL, 50 IDs)CLIP-I: 66.10 -> 73.08Improved
add RB-Guidance (ablation)OmniPortrait · Ablation (SDXL, 50 IDs)CLIP-T: 24.88 -> 24.25Hurt
add RB-Guidance (ablation)OmniPortrait · Ablation (SDXL, 50 IDs)FID: 210.45 -> 213.48Hurt
use guidance start time u = 0.6 rather than earlier or later (ablation)OmniPortrait · Ablation (SDXL, 50 IDs)identity similarity: u = 0.6Mixed
larger face localization loss weight eta (ablation)OmniPortrait · Ablation (SDXL, 50 IDs)SIM / CLIP-T: higher face similarity, lower text alignmentMixed

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