ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation
This addresses the problem of precise layout and identity control in multi-instance generation for AI image synthesis, representing a novel method rather than an incremental improvement.
The paper tackles the challenge of multi-instance image generation by introducing ContextGen, a Diffusion Transformer framework that uses layout and reference images to control object positions and preserve identities, achieving state-of-the-art results in control precision, identity fidelity, and visual quality.
Multi-instance image generation (MIG) remains a significant challenge for modern diffusion models due to key limitations in achieving precise control over object layout and preserving the identity of multiple distinct subjects. To address these limitations, we introduce ContextGen, a novel Diffusion Transformer framework for multi-instance generation that is guided by both layout and reference images. Our approach integrates two key technical contributions: a Contextual Layout Anchoring (CLA) mechanism that incorporates the composite layout image into the generation context to robustly anchor the objects in their desired positions, and Identity Consistency Attention (ICA), an innovative attention mechanism that leverages contextual reference images to ensure the identity consistency of multiple instances. Recognizing the lack of large-scale, hierarchically-structured datasets for this task, we introduce IMIG-100K, the first dataset with detailed layout and identity annotations. Extensive experiments demonstrate that ContextGen sets a new state-of-the-art, outperforming existing methods in control precision, identity fidelity, and overall visual quality.