# Seg2Any: Open-set Segmentation-Mask-to-Image Generation with Precise Shape and Semantic Control

arXiv: https://arxiv.org/abs/2506.00596 · HTML: https://mlsanity.com/paper/2506.00596/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 55 of its 66 references that are in the map.
- First posted on arXiv 31 May 2025.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 30 of 55)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [OminiControl: Minimal and Universal Control for Diffusion Transformer](https://mlsanity.com/paper/2411.15098/) (2024)
- [LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation](https://mlsanity.com/paper/2303.17189/) (2023)
- [PixelLM: Pixel Reasoning with Large Multimodal Model](https://mlsanity.com/paper/2312.02228/) (2023)
- [SpaText: Spatio-Textual Representation for Controllable Image Generation](https://mlsanity.com/paper/2211.14305/) (2022)
- [UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild](https://mlsanity.com/paper/2305.11147/) (2023)
- [InstanceDiffusion: Instance-level Control for Image Generation](https://mlsanity.com/paper/2402.03290/) (2024)
- [Dense Text-to-Image Generation with Attention Modulation](https://mlsanity.com/paper/2308.12964/) (2023)
- [Osprey: Pixel Understanding with Visual Instruction Tuning](https://mlsanity.com/paper/2312.10032/) (2023)
- [ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback](https://mlsanity.com/paper/2404.07987/) (2024)
- [PACO: Parts and Attributes of Common Objects](https://mlsanity.com/paper/2301.01795/) (2023)

## Built on by (most cited first, 10 of 10)

- [RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details](https://mlsanity.com/paper/2604.06870/) (2026)
- [3D Space as a Scratchpad for Editable Text-to-Image Generation](https://mlsanity.com/paper/2601.14602/) (2026)
- [OcclusionFormer: Arranging Z-Order for Layout-Grounded Image Generation](https://mlsanity.com/paper/2605.21343/) (2026)
- [To Blend In, First Decouple: Rethinking Camouflage Image Generation via Context-Decoupled Representations](https://mlsanity.com/paper/2607.17768/) (2026)
- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [COLLAR: Cascaded Object-Level Latent Refinement for High-Fidelity Conditional Generation](https://mlsanity.com/paper/2606.00954/) (2026)
- [InstanceControl: Controllable Complex Image Generation without Instance Labeling](https://mlsanity.com/paper/2606.31924/) (2026)
- [PhysMirror: Physics-Aware Mirror Object Generation](https://mlsanity.com/paper/2607.03470/) (2026)
- [Appearance Pointers -- Multimodal Region Control of Diffusion Transformers](https://mlsanity.com/paper/2607.19344/) (2026)
- [OccluRank: Controllable Occlusion-Aware Layout-to-Image Generation by Adding Just an Ordinal Rank](https://mlsanity.com/paper/2608.20932/) (2026)

## Abstract (arXiv)

Despite recent advances in diffusion models, top-tier text-to-image (T2I) models still struggle to achieve precise spatial layout control, i.e. accurately generating entities with specified attributes and locations. Segmentation-mask-to-image (S2I) generation has emerged as a promising solution by incorporating pixel-level spatial guidance and regional text prompts. However, existing S2I methods fail to simultaneously ensure semantic consistency and shape consistency. To address these challenges, we propose Seg2Any, a novel S2I framework built upon advanced multimodal diffusion transformers (e.g. FLUX). First, to achieve both semantic and shape consistency, we decouple segmentation mask conditions into regional semantic and high-frequency shape components. The regional semantic condition is introduced by a Semantic Alignment Attention Mask, ensuring that generated entities adhere to their assigned text prompts. The high-frequency shape condition, representing entity boundaries, is encoded as an Entity Contour Map and then introduced as an additional modality via multi-modal attention to guide image spatial structure. Second, to prevent attribute leakage across entities in multi-entity scenarios, we introduce an Attribute Isolation Attention Mask mechanism, which constrains each entity's image tokens to attend exclusively to themselves during image self-attention. To support open-set S2I generation, we construct SACap-1M, a large-scale dataset containing 1 million images with 5.9 million segmented entities and detailed regional captions, along with a SACap-Eval benchmark for comprehensive S2I evaluation. Extensive experiments demonstrate that Seg2Any achieves state-of-the-art performance on both open-set and closed-set S2I benchmarks, particularly in fine-grained spatial and attribute control of entities.