AI Paper Atlas

Research map / Image generation / Editing and style transfer

ConsistentID: Portrait Generation With Multimodal Fine-Grained Identity Preserving

Jiehui Huang, Xiao ming Dong, Wu Song, Chong Zheng, Zhenchao Tang, Jun Zhou, Yuhao Cheng, Long Chen, Hanhui Li, Yiqiang Yan, Shengcai Liao, Xiaodan Liang

TPAMI 2026 · Image generation › Editing and style transfer · approach: Diffusion face generation and editing · 55 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 facial attention localization loss L_facial (ablation)ConsistentID · Ablation (Table 2)DINO: 77.8 -> 86.1Improved
add facial attention localization loss L_facial (ablation)ConsistentID · Ablation (Table 2)CLIP-I: 66.4 -> 75.5Improved
add facial attention localization loss L_facial (ablation)ConsistentID · Ablation (Table 2)FGIS: 82.9 -> 85.6Improved
add fine-grained features to overall facial features (ablation)ConsistentID · Ablation (Table 2)DINO: 80.7 -> 86.1Improved
fine-grained features alone vs combined with overall facial ID (ablation)ConsistentID · Ablation (Table 2)DINO: 86.6 vs 86.1No clear effect
add LLaVA1.5 descriptions in training (ablation)ConsistentID · Ablation (Table 2)CLIP-I: 67.4 -> 75.3Improved
add LLaVA1.5 descriptions in training (ablation)ConsistentID · Ablation (Table 2)DINO: 84.3 -> 85.4Improved
train image projection jointly with facial encoder (ablation)ConsistentID · Ablation (Table 2)DINO: 75.6 -> 86.1Improved
train image projection jointly with facial encoder (ablation)ConsistentID · Ablation (Table 2)CLIP-I: 61.0 -> 75.5Improved
replace SD1.5 base with SDXL (ablation)ConsistentID · SDXL extension (180 images, 45 prompts)FaceSim: 62.9 -> 73.1Improved
replace SD1.5 base with SDXL (ablation)ConsistentID · SDXL extension (180 images, 45 prompts)CLIP-T: 19.8 -> 21.9Improved
replace SD1.5 base with SDXL (ablation)ConsistentID · SDXL extension (180 images, 45 prompts)Speed (s): 16 -> 18Hurt

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