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 introduce the In-context Multi-Modal Attention (ICMA) mechanism with learnable task-oriented register tokens and boundary-aware positional embeddings to enable the model to correctly handle different task types and distinguish various inputs in polyptych configurations. To bridge the data gap, we carefully curated a high-quality dataset of 12k identity-consistent samples with 8k from real-world sources and 4k from high-quality synthetic data, avoiding the overly glossy and over-saturated synthetic appearance.
IC-Custom supports various industrial applications, including try-on, accessory placement, furniture arrangement, and IP customization. Extensive evaluations on our proposed ProductBench and the publicly available DreamBench demonstrate that IC-Custom significantly outperforms community workflows, closed-source models like GPT-4o, and state-of-the-art open-source approaches. IC-Custom achieves approximately 73% higher human preference across identity consistency, harmonicity, and text alignment metrics, while training only 0.4% of the original model parameters.
Hover over the images to see the generated results - Our model seamlessly integrates reference content into target scenes
Reference
Target → Generated
Reference
Target → Generated
Reference
Target → Generated
Reference
Target → Generated
Hover over the reference images to see the generated results - Our model creates images based on text prompts while maintaining reference identity