LayerComposer: Interactive Personalized T2I via Spatially-Aware Layered Canvas
This addresses the need for interactive, multi-subject image generation for users like digital artists, though it appears incremental by building on existing personalized models.
The paper tackled the problem of limited interactive control and poor scalability in personalized text-to-image generation by introducing LayerComposer, a framework that uses a layered canvas and locking mechanism, achieving superior spatial control and identity preservation compared to state-of-the-art methods.
Despite their impressive visual fidelity, existing personalized generative models lack interactive control over spatial composition and scale poorly to multiple subjects. To address these limitations, we present LayerComposer, an interactive framework for personalized, multi-subject text-to-image generation. Our approach introduces two main contributions: (1) a layered canvas, a novel representation in which each subject is placed on a distinct layer, enabling occlusion-free composition; and (2) a locking mechanism that preserves selected layers with high fidelity while allowing the remaining layers to adapt flexibly to the surrounding context. Similar to professional image-editing software, the proposed layered canvas allows users to place, resize, or lock input subjects through intuitive layer manipulation. Our versatile locking mechanism requires no architectural changes, relying instead on inherent positional embeddings combined with a new complementary data sampling strategy. Extensive experiments demonstrate that LayerComposer achieves superior spatial control and identity preservation compared to the state-of-the-art methods in multi-subject personalized image generation.