mlsanityData to 14 Oct 2026

ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation

arXiv 2510.11000 ↗First posted 13 Oct 2025cs.CVcited by 18

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

Multi-instance image generation (MIG) remains a significant challenge for modern diffusion models due to key limitations in achieving precise control over object layout and preserving the identity of multiple distinct subjects. To address these limitations, we introduce ContextGen, a novel Diffusion Transformer framework for multi-instance generation that is guided by both layout and reference images. Our approach integrates two key technical contributions: a Contextual Layout Anchoring (CLA) mechanism that incorporates the composite layout image into the generation context to robustly anchor the objects in their desired positions, and Identity Consistency Attention (ICA), an innovative attention mechanism that leverages contextual reference images to ensure the identity consistency of multiple instances. To address the absence of a large-scale, high-quality dataset for this task, we introduce IMIG-100K, the first dataset to provide detailed layout and identity annotations specifically designed for Multi-Instance Generation. Extensive experiments demonstrate that ContextGen sets a new state-of-the-art, outperforming existing methods especially in layout control and identity fidelity.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 41 of its 57 references that are in the map. First posted on arXiv 13 Oct 2025.

Builds on

41 of 57 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer1 Aug
  2. 2025XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation26 Jun
  3. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space17 Jun
  4. 2025In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer29 Apr
  5. 2025OminiControl2: Efficient Conditioning for Diffusion Transformers11 Mar
  6. 2025EliGen: Entity-Level Controlled Image Generation with Regional Attention2 Jan
  7. 2024CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation5 Dec
  8. 2024OmniGen: Unified Image Generation17 Sep
  9. 2023GLIGEN: Open-Set Grounded Text-to-Image Generation17 Jan

Other references · 32

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  6. 2022Scalable Diffusion Models with Transformerscited by 6,054
  7. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  8. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  9. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  10. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  11. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 977
  12. 2024mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Modelscited by 291
20 more
  1. 2025OmniGen2: Towards Instruction-Aligned Multimodal Generationcited by 253
  2. 2025Less-to-More Generalization: Unlocking More Controllability by In-Context Generationcited by 154
  3. 2024MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidancecited by 144
  4. 2023Prodigy: An Expeditiously Adaptive Parameter-Free Learnercited by 133
  5. 2024DreamBench++: A Human-Aligned Benchmark for Personalized Image Generationcited by 131
  6. 2024MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesiscited by 124
  7. 2013Stabilitycited by 120
  8. 2021Sample and Computation Redistribution for Efficient Face Detectioncited by 89
  9. 2025DreamO: A Unified Framework for Image Customizationcited by 83
  10. 2021CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiabilitycited by 69
  11. 2025Insert Anything: Image Insertion via In-Context Editing in DiTcited by 61
  12. 2024Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generatorcited by 48
  13. 2024Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generationcited by 43
  14. 2024MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMscited by 39
  15. 20243DIS: Depth-Driven Decoupled Instance Synthesis for Text-to-Image Generationcited by 37
  16. 2024MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesiscited by 35
  17. 2025DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Modelscited by 28
  18. 2025DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergycited by 13
  19. 2023Controllable 3D Face Generation with Conditional Style Code Diffusioncited by 9
  20. 2025PositionIC: Unified Position and Identity Consistency for Image Customizationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 16.

18 papers.

Sort:

By area:

  1. 2026From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmarkcited by 7
  2. 2025ConsistCompose: Unified Multimodal Layout Control for Image Compositioncited by 5
  3. 2026Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformerscited by 5
  4. 2026RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Detailscited by 5
  5. 2025Are Image-to-Video Models Good Zero-Shot Image Editors?cited by 4
  6. 2026MultiBind: A Benchmark for Attribute Misbinding in Multi-Subject Generationcited by 4
  7. 2026Scaling Multi-Reference Image Generation with Dynamic Reward Optimizationcited by 3
  8. 2026Spatial Chain-of-Thought: Bridging Understanding and Generation Models for Spatial Reasoning Generationcited by 2
  9. 2026Composing Driving Worlds through Disentangled Control for Adversarial Scenario Generationcited by 2
  10. 2026FoleyDirector: Fine-Grained Temporal Steering for Video-to-Audio Generation via Structured Scriptscited by 2
  11. 2026When Identities Collapse: A Stress-Test Benchmark for Multi-Subject Personalizationcited by 2
  12. 2026TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Maskingcited by 2
6 more
  1. 2026PhyEdit: Towards Real-World Object Manipulation via Physically-Grounded Image Editingcited by 1
  2. 2026AnyPhoto: Multi-Person Identity Preserving Image Generation with ID Adaptive Modulation on Location Canvascited by 0
  3. 2026Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generationcited by 0
  4. 2026ControlRef: Efficient Layout-Guided Multi-Instance Generation via Anchored 4D-RoPEcited by 0
  5. 2026AutoRef: Harness Optimization for Agentic Multi-Reference Image Generationcited by 0
  6. 2026VIF-Bench: Evaluating Visual Instruction Following in Multi-Reference Image Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Create Anything Anywhere: Layout-Controllable Personalized Diffusion Model for Multiple Subjects
  2. 2024IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation
  3. 2025InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention
  4. 2024LayoutDiT: Exploring Content-Graphic Balance in Layout Generation with Diffusion Transformer
  5. 2024LocRef-Diffusion:Tuning-Free Layout and Appearance-Guided Generation
  6. 2025UniLayDiff: A Unified Diffusion Transformer for Content-Aware Layout Generation
  7. 2024Obtaining Favorable Layouts for Multiple Object Generation
  8. 2024Training-free Composite Scene Generation for Layout-to-Image Synthesis