CVLGApr 2, 2025

Less-to-More Generalization: Unlocking More Controllability by In-Context Generation

arXiv:2504.02160v1131 citationsh-index: 9
Originality Incremental advance
AI Analysis

This work addresses scalability and expansibility issues in subject-driven image generation, which is incremental as it builds on existing diffusion transformer methods.

The paper tackles challenges in subject-driven image generation, specifically data scalability and subject expansibility for multi-subject scenarios, by proposing a data synthesis pipeline and a model called UNO, achieving high consistency and controllability in both single- and multi-subject generation.

Although subject-driven generation has been extensively explored in image generation due to its wide applications, it still has challenges in data scalability and subject expansibility. For the first challenge, moving from curating single-subject datasets to multiple-subject ones and scaling them is particularly difficult. For the second, most recent methods center on single-subject generation, making it hard to apply when dealing with multi-subject scenarios. In this study, we propose a highly-consistent data synthesis pipeline to tackle this challenge. This pipeline harnesses the intrinsic in-context generation capabilities of diffusion transformers and generates high-consistency multi-subject paired data. Additionally, we introduce UNO, which consists of progressive cross-modal alignment and universal rotary position embedding. It is a multi-image conditioned subject-to-image model iteratively trained from a text-to-image model. Extensive experiments show that our method can achieve high consistency while ensuring controllability in both single-subject and multi-subject driven generation.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes