Papers
arxiv:2511.21691

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

Published on Nov 26
· Submitted by Yusuf Dalva on Nov 28
#2 Paper of the day
Authors:
,
,
,
,
,
,

Abstract

Canvas-to-Image is a unified framework that encodes diverse control signals into a composite canvas image for high-fidelity multimodal image generation, outperforming existing methods in various benchmarks.

AI-generated summary

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.

Community

Paper author Paper submitter

While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control. We introduce Canvas-to-Image, a unified framework that consolidates these heterogeneous controls into a single canvas interface. Our key idea is to encode diverse control signals, including subject references, bounding boxes, and pose skeletons, into a single composite canvas image that the model can directly interpret for integrated visual-spatial reasoning.

where can we try the demo??

How is the image consistency, e.g. with successive images (video)?

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

This needs added to ComfyUI asap!

Where is download code for Comfy node?

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2511.21691 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2511.21691 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2511.21691 in a Space README.md to link it from this page.

Collections including this paper 8