Research map / Image generation / Text-to-image diffusion
SAEdit: Token-Level Control for Continuous Image Editing via Sparse Autoencoder
Ronen Kamenetsky, Sara Dorfman, Daniel Garibi, Roni Paiss, Or Patashnik, Danny Cohen-Or
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use SAEdit instead of Flux Space | Flux · User study | prompt adherence win rate: 92% | Improved |
| use SAEdit instead of Flux Kontext (CFG) for continuous edit control | Flux · User study | overall win rate: 70% | Improved |
| use SAEdit instead of ConceptSlider (Flux) | Flux · User study | overall win rate: 71% | Improved |
| add aggregation of N prompt pairs to single-pair direction (ablation) | SAEdit · quantitative ablation benchmark | VQA score | Improved |
| add exponential injection schedule (ablation) | SAEdit · quantitative ablation benchmark | LPIPS | Improved |
Closest papers by meaning
- EditInfinity: Image Editing with Binary-Quantized Generative Models (NeurIPS 2025 · similarity 0.88)
- Prompt Augmentation for Self-supervised Text-guided Image Manipulation (CVPR 2024 · similarity 0.88)
- AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea (CVPR 2025 · similarity 0.88)
- Textualize Visual Prompt for Image Editing via Diffusion Bridge (AAAI 2025 · similarity 0.88)
- Text-Driven Image Editing via Learnable Regions (CVPR 2024 · similarity 0.88)
- AdapEdit: Spatio-Temporal Guided Adaptive Editing Algorithm for Text-Based Continuity-Sensitive Image Editing (AAAI 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
