Canvas-to-Image: Compositional Image Generation with Multimodal Controls

TL;DR

Canvas-to-Image introduces a unified diffusion framework that integrates diverse multimodal controls into image generation, enabling faithful, high-quality compositional images through a novel multi-task training approach.

Contribution

It proposes a novel multi-task training strategy that allows diffusion models to jointly interpret and integrate heterogeneous control signals from a unified canvas interface.

Findings

Outperforms state-of-the-art in identity preservation and control adherence.

Excels in multi-person, pose-controlled, and layout-constrained image generation.

Generalizes well to multi-control scenarios during inference.

Abstract

While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control, particularly when users simultaneously specify text prompts, subject references, spatial arrangements, pose constraints, and layout annotations. We introduce Canvas-to-Image, a unified framework that consolidates these heterogeneous controls into a single canvas interface, enabling users to generate images that faithfully reflect their intent. Our key idea is to encode diverse control signals into a single composite canvas image that the model can directly interpret for integrated visual-spatial reasoning. We further curate a suite of multi-task datasets and propose a Multi-Task Canvas Training strategy that optimizes the diffusion model to jointly understand and integrate heterogeneous controls into text-to-image generation within a unified learning paradigm. This joint training enables Canvas-to-Image to reason across multiple control modalities rather than relying on task-specific heuristics, and it generalizes well to multi-control scenarios during inference. Extensive experiments show that Canvas-to-Image significantly outperforms state-of-the-art methods in identity preservation and control adherence across challenging benchmarks, including multi-person composition, pose-controlled composition, layout-constrained generation, and multi-control generation.