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

• URL: http://arxiv.org/abs/2511.21691v1
• Date: Wed, 26 Nov 2025 18:59:56 GMT
• Title: Canvas-to-Image: Compositional Image Generation with Multimodal Controls
• Authors: Yusuf Dalva, Guocheng Gordon Qian, Maya Goldenberg, Tsai-Shien Chen, Kfir Aberman, Sergey Tulyakov, Pinar Yanardag, Kuan-Chieh Jackson Wang,
• Abstract summary: We introduce Canvas-to-Image, a unified framework that consolidates heterogeneous controls into a single canvas interface.<n>Our key idea is to encode diverse control signals into a single composite canvas image that the model can interpret for integrated visual-spatial reasoning.
• Score: 51.44122945214702
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• MoGen: A Unified Collaborative Framework for Controllable Multi-Object Image Generation [76.94658056824422]
  MoGen is a user-friendly multi-object image generation method.<n>First, we design a Regional Semantic Anchor (RSA) module that precisely anchors phrase units in language descriptions to their corresponding image regions.<n>We introduce an Adaptive Multi-modal Guidance (AMG) module, which adaptively parses and integrates various combinations of multi-source control signals.
  arXiv  Detail & Related papers  (2026-01-09T05:57:48Z)
• Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach [99.80480649258557]
  DiTFuse is an instruction-driven framework that performs semantics-aware fusion within a single model.<n>Experiments on public IVIF, MFF, and MEF benchmarks confirm superior quantitative and qualitative performance, sharper textures, and better semantic retention.
  arXiv  Detail & Related papers  (2025-12-08T05:04:54Z)
• ConsistCompose: Unified Multimodal Layout Control for Image Composition [56.909072845166264]
  We present ConsistCompose, a unified framework that embeds layout coordinates directly into language prompts.<n>We show that ConsistCompose substantially improves spatial accuracy over layout-controlled baselines.
  arXiv  Detail & Related papers  (2025-11-23T08:14:53Z)
• ControlThinker: Unveiling Latent Semantics for Controllable Image Generation through Visual Reasoning [76.2503352325492]
  ControlThinker is a novel framework that employs a "comprehend-then-generate" paradigm.<n>Latent semantics from control images are mined to enrich text prompts.<n>This enriched semantic understanding then seamlessly aids in image generation without the need for additional complex modifications.
  arXiv  Detail & Related papers  (2025-06-04T05:56:19Z)
• ComposeAnyone: Controllable Layout-to-Human Generation with Decoupled Multimodal Conditions [74.30040551058319]
  ComposeAnyone is a controllable layout-to-human generation method with decoupled multimodal conditions.<n>Our dataset provides decoupled text and reference image annotations for different components of each human image.<n>Experiments on multiple datasets demonstrate that ComposeAnyone generates human images with better alignment to given layouts.
  arXiv  Detail & Related papers  (2025-01-21T14:32:47Z)
• UNIC-Adapter: Unified Image-instruction Adapter with Multi-modal Transformer for Image Generation [64.8341372591993]
  We propose a new approach to unify controllable generation within a single framework.<n>Specifically, we propose the unified image-instruction adapter (UNIC-Adapter) built on the Multi-Modal-Diffusion Transformer architecture.<n>Our UNIC-Adapter effectively extracts multi-modal instruction information by incorporating both conditional images and task instructions.
  arXiv  Detail & Related papers  (2024-12-25T15:19:02Z)
• Generating Compositional Scenes via Text-to-image RGBA Instance Generation [82.63805151691024]
  Text-to-image diffusion generative models can generate high quality images at the cost of tedious prompt engineering. We propose a novel multi-stage generation paradigm that is designed for fine-grained control, flexibility and interactivity. Our experiments show that our RGBA diffusion model is capable of generating diverse and high quality instances with precise control over object attributes.
  arXiv  Detail & Related papers  (2024-11-16T23:44:14Z)
• OmniBooth: Learning Latent Control for Image Synthesis with Multi-modal Instruction [32.08995899903304]
  We present OmniBooth, an image generation framework that enables spatial control with instance-level multi-modal customization. Our approach significantly expands the scope of text-to-image generation, and elevates it to a more versatile and practical dimension in controllability.
  arXiv  Detail & Related papers  (2024-10-07T11:26:13Z)
• AnyControl: Create Your Artwork with Versatile Control on Text-to-Image Generation [24.07613591217345]
  Linguistic control enables effective content creation, but struggles with fine-grained control over image generation. AnyControl develops a novel Multi-Control framework that extracts a unified multi-modal embedding to guide the generation process. This approach enables a holistic understanding of user inputs, and produces high-quality, faithful results under versatile control signals.
  arXiv  Detail & Related papers  (2024-06-27T07:40:59Z)
• MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation [34.61940502872307]
  MultiDiffusion is a unified framework that enables versatile and controllable image generation. We show that MultiDiffusion can be readily applied to generate high quality and diverse images.
  arXiv  Detail & Related papers  (2023-02-16T06:28:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.