# LCG: Long-Context Consistent Image Generation with Sparse Relational Attention

arXiv: https://arxiv.org/abs/2606.26171 · HTML: https://mlsanity.com/paper/2606.26171/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 24 Jun 2026.

## Builds on (most cited first, 17 of 17)

- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [InstantID: Zero-shot Identity-Preserving Generation in Seconds](https://mlsanity.com/paper/2401.07519/) (2024)
- [Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention](https://mlsanity.com/paper/2502.11089/) (2025)
- [OminiControl: Minimal and Universal Control for Diffusion Transformer](https://mlsanity.com/paper/2411.15098/) (2024)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [Less-to-More Generalization: Unlocking More Controllability by In-Context Generation](https://mlsanity.com/paper/2504.02160/) (2025)
- [DreamO: A Unified Framework for Image Customization](https://mlsanity.com/paper/2504.16915/) (2025)
- [Captain Cinema: Towards Short Movie Generation](https://mlsanity.com/paper/2507.18634/) (2025)
- [DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusion](https://mlsanity.com/paper/2407.12899/) (2024)
- [Story2Board: A Training-Free Approach for Expressive Storyboard Generation](https://mlsanity.com/paper/2508.09983/) (2025)
- [Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models](https://mlsanity.com/paper/2504.03140/) (2025)
- [IC-Custom: Diverse Image Customization via In-Context Learning](https://mlsanity.com/paper/2507.01926/) (2025)
- [Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection](https://mlsanity.com/paper/2409.19624/) (2024)
- [Object Isolated Attention for Consistent Story Visualization](https://mlsanity.com/paper/2503.23353/) (2025)

## Abstract (arXiv)

Recent image generation models achieve impressive quality in single-image synthesis, but often fail to maintain consistency across sequential outputs, as required in comics, storyboards, and visual narratives. We propose Long-Context Generation (LCG), a framework for long-context multi-image text-to-image generation, to improve consistency and scalability in long-context multi-image generation. LCG employs the Sparse Relational Attention (SRA) mechanism to selectively attend to core features across extended visual contexts, ensuring that the propagation of semantic and layout information remains computationally tractable. To enforce semantic alignment, we introduce the Routing Consistency Constraint (RCC), which leverages identity-aware masks to align structural patterns across generation branches, effectively mitigating drift in appearance even in complex multi-character scenes. To support training and evaluation in this setting, we construct the Long-Context Consistency Dataset (LCCD), a large-scale synthetic dataset comprising character-centric multi-image sequences spanning varied situational contexts. LCCD contains 600K training sequences and a separate 1K test set, with each sequence containing 6 to 20 images. The experiments demonstrate that LCG outperforms the compared baselines in prompt alignment and character consistency for long-context image generation, including multi-character scenes.