SAEdit: Token-Level Control for Continuous Image Editing via Sparse Autoencoder

Large-scale text-to-image dix001Busion models have become thebackbone of modern image editing, yet text prompts alone do not ox001Beradequate control over the editing process. Two properties are especiallydesirable: disentanglement, where changing one attribute does not un-intentionally alter others, and continuous control, where the strengthof an edit can be smoothly adjusted. We introduce a method for dis-entangled and continuous editing through token-level manipulation oftext embeddings. The edits are applied by manipulating the embeddingsalong carefully chosen directions, which control the strength of the tar-get attribute. To identify such directions, we employ a Sparse Autoen-coder (SAE), whose sparse latent space exposes semantically isolateddimensions. Our method operates directly on text embeddings withoutmodifying the dix001Busion process, making it model agnostic and broadlyapplicable to various image synthesis backbones. Experiments show thatit enables intuitive and ex001Ecient manipulations with continuous controlacross diverse attributes and domains.