# SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder arXiv: https://arxiv.org/abs/2510.05081 ยท HTML: https://mlsanity.com/paper/2510.05081/ ## Key facts - Cited by 9 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 48 of its 56 references that are in the map. - First posted on arXiv 6 Oct 2025. ## Placed in - Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/) - Mechanistic interpretability / [Interpreting and steering diffusion models](https://mlsanity.com/mechinterp/interpreting-and-steering-diffusion-models/) ## Builds on (most cited first, 30 of 48) - [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019) - [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018) - [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020) - [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020) - [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022) - [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022) - [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023) - [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) - [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023) - [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022) - [Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2211.12572/) (2022) - [MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing](https://mlsanity.com/paper/2304.08465/) (2023) - [Zero-shot Image-to-Image Translation](https://mlsanity.com/paper/2302.03027/) (2023) - [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024) - [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://mlsanity.com/paper/2210.14896/) (2022) - [Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models](https://mlsanity.com/paper/2305.16807/) (2023) - [Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations](https://mlsanity.com/paper/2410.10792/) (2024) - [Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models](https://mlsanity.com/paper/2311.12092/) (2023) - [LEDITS++: Limitless Image Editing using Text-to-Image Models](https://mlsanity.com/paper/2311.16711/) (2023) - [Learning Multi-Level Features with Matryoshka Sparse Autoencoders](https://mlsanity.com/paper/2503.17547/) (2025) - [Localizing Object-level Shape Variations with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.11306/) (2023) - [Cross-Image Attention for Zero-Shot Appearance Transfer](https://mlsanity.com/paper/2311.03335/) (2023) - [BatchTopK Sparse Autoencoders](https://mlsanity.com/paper/2412.06410/) (2024) - [ReNoise: Real Image Inversion Through Iterative Noising](https://mlsanity.com/paper/2403.14602/) (2024) - [Improving Tuning-Free Real Image Editing with Proximal Guidance](https://mlsanity.com/paper/2306.05414/) (2023) - [SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders](https://mlsanity.com/paper/2501.18052/) (2025) - [SAEs Are Good for Steering -- If You Select the Right Features](https://mlsanity.com/paper/2505.20063/) (2025) ## Built on by (most cited first, 9 of 9) - [The Unreasonable Effectiveness of Text Embedding Interpolation for Continuous Image Steering](https://mlsanity.com/paper/2603.17998/) (2026) - [ELROND: Exploring and decomposing intrinsic capabilities of diffusion models](https://mlsanity.com/paper/2602.10216/) (2026) - [PixelSmile: Toward Fine-Grained Facial Expression Editing](https://mlsanity.com/paper/2603.25728/) (2026) - [TokenDial: Continuous Attribute Control for Text-to-Video Generation in Visual Dial Space](https://mlsanity.com/paper/2603.27520/) (2026) - [Thinking in Boxes: 3D Editing in Real Images Made Easy](https://mlsanity.com/paper/2606.20556/) (2026) - [Token-to-Token Alignment of Text Embeddings for Semantic Blending](https://mlsanity.com/paper/2606.24021/) (2026) - [Latent-Identity Tuning in Text-to-Image Personalization Models](https://mlsanity.com/paper/2607.11885/) (2026) - [Diffusion Image Editing via Asynchronous Token Decoding](https://mlsanity.com/paper/2608.09322/) (2026) - [Scalable Minimal-Change Learning for Controllable Image Editing](https://mlsanity.com/paper/2610.06021/) (2026) ## Abstract (arXiv) Large-scale text-to-image diffusion models have become the backbone of modern image editing, yet text prompts alone do not offer adequate control over the editing process. Two properties are especially desirable: disentanglement, where changing one attribute does not unintentionally alter others, and continuous control, where the strength of an edit can be smoothly adjusted. We introduce a method for disentangled and continuous editing through token-level manipulation of text embeddings. The edits are applied by manipulating the embeddings along carefully chosen directions, which control the strength of the target attribute. To identify such directions, we employ a Sparse Autoencoder (SAE), whose sparse latent space exposes semantically isolated dimensions. Our method operates directly on text embeddings without modifying the diffusion process, making it model agnostic and broadly applicable to various image synthesis backbones. Experiments show that it enables intuitive and efficient manipulations with continuous control across diverse attributes and domains.