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

Source: [IC-Custom: Diverse Image Customization via In-Context Learning](<https://www.sota2.com/research/paper/68fa7bc01e209131cea8a2e8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:47:25.110Z

Authors: Yaowei Li, Xiaoyu Li, Zhaoyang Zhang, Yuxuan Bian, Gan Liu, Xinyuan Li, Jiale Xu, Wenbo Hu, Yating Liu, Lingen Li, Jing Cai, Yuexian Zou, Yancheng He, Ying Shan

Published: 2025-07-02T17:36:38.000Z

## Abstract

Image customization, a crucial technique for industrial media production, aims to generate content that is consistent with reference images. However, current approaches conventionally separate image customization into position-aware and position-free customization paradigms and lack a universal framework for diverse customization, limiting their applications across various scenarios. To overcome these limitations, we propose IC-Custom, a unified framework that seamlessly integrates position-aware and position-free image customization through in-context learning. IC-Custom concatenates reference images with target images to a polyptych, leveraging DiT's multi-modal attention mechanism for fine-grained token-level interactions. We propose the In-context Multi-Modal Attention (ICMA) mechanism, which employs learnable task-oriented register tokens and boundary-aware positional embeddings to enable the model to effectively handle diverse tasks and distinguish between inputs in polyptych configurations. To address the data gap, we curated a 12K identity-consistent dataset with 8K real-world and 4K high-quality synthetic samples, avoiding the overly glossy, oversaturated look typical of synthetic data. IC-Custom supports various industrial applications, including try-on, image insertion, and creative IP customization. Extensive evaluations on our proposed ProductBench and the publicly available DreamBench demonstrate that IC-Custom significantly outperforms community workflows, closed-source models, and state-of-the-art open-source approaches. IC-Custom achieves about 73\\% higher human preference across identity consistency, harmony, and text alignment metrics, while training only 0.4\\% of the original model parameters. Project page: https://liyaowei-stu.github.io/project/IC\_Custom

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on DreamAssembly](<https://www.sota2.com/research/sota/image-classification-on-dreamassembly.md>): Image Classification; DreamAssembly; Accuracy: 21.33.

- [Image Synthesis on DreamAssembly (test)](<https://www.sota2.com/research/sota/image-synthesis-on-dreamassembly-test.md>): Image Synthesis; DreamAssembly (test); CLIP-I: 0.7011.

- [Image Synthesis on MureCom](<https://www.sota2.com/research/sota/image-synthesis-on-murecom.md>): Image Synthesis; MureCom; CLIP-I: 0.7891.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2507.01926>)

[PDF](<https://arxiv.org/pdf/2507.01926.pdf>)