AI Paper Atlas

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

IC-Custom: Diverse Image Customization via In-Context Learning

Yaowei Li, Xiaoyu Li, Zhaoyang Zhang, Yuxuan Bian, Gan Liu, Xinyuan Li, Jiale Xu, Wenbo Hu, yating liu, Lingen Li, Jing Cai, Yuexian Zou and 2 more

ICLR 2026 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization · 10 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 input-layer training of DiT image and text layers (ablation)IC-Custom · ProductBench (precise mask)DINO-I: 62.00 -> 63.14Improved
add input-layer training (ablation)IC-Custom · ProductBench (user-drawn mask)DINO-I: 62.13 -> 63.28Improved
add real data to synthetic training data (ablation)IC-Custom · ProductBench (precise mask)DINO-I: 62.38 -> 63.14Improved
add user-drawn mask data in training (ablation)IC-Custom · ProductBench (user-drawn mask)DINO-I: 61.30 -> 63.28Improved
add task-oriented register tokens (ablation)IC-Custom · ProductBench (precise mask)DINO-I: 63.00 -> 63.14Improved
add boundary-aware positional embeddings (ablation)IC-Custom · ProductBench (precise mask)CLIP-I: 81.31 -> 81.92Improved
add task-oriented register tokens (ablation)IC-Custom · ProductBench (user-drawn mask)CLIP-T: 31.33 -> 31.80Improved
fine-tune on customization data versus zero-shot (ablation)IC-Custom · ProductBench (precise mask)DINO-I: 55.49 -> 63.14Improved
compare unified IC-Custom against ACE++ task-specific LoRAIC-Custom · ProductBench (precise mask)DINO-I: 60.68 -> 63.14Improved
compare IC-Custom against best baseline FLUX.1 workflowIC-Custom · ProductBench (user-drawn mask)DINO-I: 63.28 vs. 62.26Improved
compare IC-Custom against DreamOIC-Custom · DreamBench (position-free)DINO: 57.69 -> 65.67Improved

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