mlsanityData to 7 Oct 2026

STEPS: Scene Text Editing with Preserved Style Using Diffusion and Contrastive Style Encoding

arXiv 2609.38636 ↗First posted 29 Sep 2026cs.CV cs.LGcited by 0

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

We introduce Scene Text Editing with Preserved Style (STEPS), a novel diffusion model architecture for quality text replacement in images. Scene Text Editing (STE), also known as Visual Text Editing, consists of changing the textual content in an image while conserving the original style, e.g. font, colors, orientation, background, etc. STEPS advances the state of the art in STE through directed focus on improved style preservation. We introduce a style encoder for visual text that captures style independently of textual content, and a model architecture that combines the style encoder with multiple semantic conditions (target text characters encoding and rendered glyphs). STEPS achieves superior results to previous STE methods in style preservation, output readability, and subjective quality.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 15 of its 16 references that are in the map. First posted on arXiv 29 Sep 2026.

Builds on

15 of 16 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editing6 May
  2. 2023TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering28 Nov
  3. 2023AnyText: Multilingual Visual Text Generation And Editing6 Nov
  4. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models13 Aug
  5. 2023DiffUTE: Universal Text Editing Diffusion Model18 May
  6. 2023Improving Diffusion Models for Scene Text Editing with Dual Encoders12 Apr
  7. 2022Blended Latent Diffusion6 Jun

Other references · 8

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  3. 2021TrOCR: Transformer-based Optical Character Recognition with Pre-trained Modelscited by 278
  4. 2024FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Modelscited by 214
  5. 2022Character-Aware Models Improve Visual Text Renderingcited by 90
  6. 2024AnyText2: Visual Text Generation and Editing With Customizable Attributescited by 48
  7. 2024TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Controlcited by 44
  8. 2022Exploring Stroke-Level Modifications for Scene Text Editingcited by 36

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025SceneTextStylizer: A Training-Free Scene Text Style Transfer Framework with Diffusion Model
  2. 2023On Manipulating Scene Text in the Wild with Diffusion Models
  3. 2026Salvation Lies Within: Eliciting Inherent Style Transfer in Step-Distilled Diffusion Models
  4. 2023ControlStyle: Text-Driven Stylized Image Generation Using Diffusion Priors
  5. 2026Self-Prompting Diffusion Transformer for Open-Vocabulary Scene Text Editing via In-Context Learning
  6. 2024InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation
  7. 2024TextMastero: Mastering High-Quality Scene Text Editing in Diverse Languages and Styles
  8. 2023Design Booster: A Text-Guided Diffusion Model for Image Translation with Spatial Layout Preservation