# Consistent text-to-image generation via scene de-contextualization

arXiv: https://arxiv.org/abs/2510.14553 · HTML: https://mlsanity.com/paper/2510.14553/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 41 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Builds on (most cited first, 30 of 34)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://mlsanity.com/paper/2305.14720/) (2023)
- [InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning](https://mlsanity.com/paper/2304.03411/) (2023)
- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding](https://mlsanity.com/paper/2312.04461/) (2023)
- [Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion](https://mlsanity.com/paper/2212.06135/) (2022)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis](https://mlsanity.com/paper/2008.05865/) (2020)
- [Training-Free Consistent Text-to-Image Generation](https://mlsanity.com/paper/2402.03286/) (2024)
- [Make-A-Story: Visual Memory Conditioned Consistent Story Generation](https://mlsanity.com/paper/2211.13319/) (2022)
- [The Chosen One: Consistent Characters in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2311.10093/) (2023)
- [ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models](https://mlsanity.com/paper/2403.01807/) (2024)
- [Source-Free Domain Adaptation with Frozen Multimodal Foundation Model](https://mlsanity.com/paper/2311.16510/) (2023)
- [JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation](https://mlsanity.com/paper/2407.06187/) (2024)
- [One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt](https://mlsanity.com/paper/2501.13554/) (2025)
- [Diffusion Self-Distillation for Zero-Shot Customized Image Generation](https://mlsanity.com/paper/2411.18616/) (2024)
- [AnimateAnything: Consistent and Controllable Animation for Video Generation](https://mlsanity.com/paper/2411.10836/) (2024)
- [A Survey on Personalized Content Synthesis with Diffusion Models](https://mlsanity.com/paper/2405.05538/) (2024)
- [StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion](https://mlsanity.com/paper/2404.05979/) (2024)

## Built on by (most cited first, 1 of 1)

- [T2LSC-Bench: Benchmarking Localized Semantic Control in Text-to-Image Generation](https://mlsanity.com/paper/2609.02255/) (2026)

## Abstract (arXiv)

Consistent text-to-image (T2I) generation seeks to produce identity-preserving images of the same subject across diverse scenes, yet it often fails due to a phenomenon called identity (ID) shift. Previous methods have tackled this issue, but typically rely on the unrealistic assumption of knowing all target scenes in advance. This paper reveals that a key source of ID shift is the native correlation between subject and scene context, called scene contextualization, which arises naturally as T2I models fit the training distribution of vast natural images. We formally prove the near-universality of this scene-ID correlation and derive theoretical bounds on its strength. On this basis, we propose a novel, efficient, training-free prompt embedding editing approach, called Scene De-Contextualization (SDeC), that imposes an inversion process of T2I's built-in scene contextualization. Specifically, it identifies and suppresses the latent scene-ID correlation within the ID prompt's embedding by quantifying the SVD directional stability to adaptively re-weight the corresponding eigenvalues. Critically, SDeC allows for per-scene use (one scene per prompt) without requiring prior access to all target scenes. This makes it a highly flexible and general solution well-suited to real-world applications where such prior knowledge is often unavailable or varies over time. Experiments demonstrate that SDeC significantly enhances identity preservation while maintaining scene diversity.