ProEdit: Inversion-based Editing From Prompts Done Right

• URL: http://arxiv.org/abs/2512.22118v1
• Date: Fri, 26 Dec 2025 18:59:14 GMT
• Title: ProEdit: Inversion-based Editing From Prompts Done Right
• Authors: Zhi Ouyang, Dian Zheng, Xiao-Ming Wu, Jian-Jian Jiang, Kun-Yu Lin, Jingke Meng, Wei-Shi Zheng,
• Abstract summary: Inversion-based visual editing provides an effective and training-free way to edit an image or a video based on user instructions.<n>Existing methods typically inject source image information during the sampling process to maintain editing consistency.<n>We propose ProEdit to address this issue both in the attention and the latent aspects.
• Score: 63.554692704101
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Inversion-based visual editing provides an effective and training-free way to edit an image or a video based on user instructions. Existing methods typically inject source image information during the sampling process to maintain editing consistency. However, this sampling strategy overly relies on source information, which negatively affects the edits in the target image (e.g., failing to change the subject's atributes like pose, number, or color as instructed). In this work, we propose ProEdit to address this issue both in the attention and the latent aspects. In the attention aspect, we introduce KV-mix, which mixes KV features of the source and the target in the edited region, mitigating the influence of the source image on the editing region while maintaining background consistency. In the latent aspect, we propose Latents-Shift, which perturbs the edited region of the source latent, eliminating the influence of the inverted latent on the sampling. Extensive experiments on several image and video editing benchmarks demonstrate that our method achieves SOTA performance. In addition, our design is plug-and-play, which can be seamlessly integrated into existing inversion and editing methods, such as RF-Solver, FireFlow and UniEdit.

Related papers

• FREE-Edit: Using Editing-aware Injection in Rectified Flow Models for Zero-shot Image-Driven Video Editing [12.549184989151135]
  Image-driven video editing aims to propagate edit contents from the modified first frame to the rest frames.<n>Current methods usually invert the source video to noise using a pre-trained image-to-video (I2V) model and then guide the sampling process using the edited first frame.<n>We propose an Editing-awaRE (REE) injection method to modulate injection intensity of each token.
  arXiv  Detail & Related papers  (2026-03-01T16:01:44Z)
• Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image Manipulation [4.404496835736175]
  Key strategy for effective image editing involves inverting the source image into editable noise maps associated with the target image.<n>We propose Editable Noise Map Inversion (ENM Inversion), a novel inversion technique that searches for optimal noise maps to ensure both content preservation and editability.<n>Our approach can also be easily applied to video editing, enabling temporal consistency and content manipulation across frames.
  arXiv  Detail & Related papers  (2025-09-30T04:44:53Z)
• Edicho: Consistent Image Editing in the Wild [90.42395533938915]
  Edicho steps in with a training-free solution based on diffusion models.<n>It features a fundamental design principle of using explicit image correspondence to direct editing.
  arXiv  Detail & Related papers  (2024-12-30T16:56:44Z)
• TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models [53.757752110493215]
  We focus on a popular line of text-based editing frameworks - the edit-friendly'' DDPM-noise inversion approach. We analyze its application to fast sampling methods and categorize its failures into two classes: the appearance of visual artifacts, and insufficient editing strength. We propose a pseudo-guidance approach that efficiently increases the magnitude of edits without introducing new artifacts.
  arXiv  Detail & Related papers  (2024-08-01T17:27:28Z)
• InstructBrush: Learning Attention-based Instruction Optimization for Image Editing [54.07526261513434]
  InstructBrush is an inversion method for instruction-based image editing methods. It extracts editing effects from image pairs as editing instructions, which are further applied for image editing. Our approach achieves superior performance in editing and is more semantically consistent with the target editing effects.
  arXiv  Detail & Related papers  (2024-03-27T15:03:38Z)
• DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing [66.43179841884098]
  Large-scale Text-to-Image (T2I) diffusion models have revolutionized image generation over the last few years. We propose DiffEditor to rectify two weaknesses in existing diffusion-based image editing. Our method can efficiently achieve state-of-the-art performance on various fine-grained image editing tasks.
  arXiv  Detail & Related papers  (2024-02-04T18:50:29Z)
• Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training [61.984277261016146]
  We propose a CustomNeRF model that unifies a text description or a reference image as the editing prompt. To tackle the first challenge, we propose a Local-Global Iterative Editing (LGIE) training scheme that alternates between foreground region editing and full-image editing. For the second challenge, we also design a class-guided regularization that exploits class priors within the generation model to alleviate the inconsistency problem.
  arXiv  Detail & Related papers  (2023-12-04T06:25:06Z)
• Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code [19.988947272980848]
  "Direct Inversion" is a novel technique achieving optimal performance of both branches with just three lines of code. We present PIE-Bench, an editing benchmark with 700 images showcasing diverse scenes and editing types. Compared to state-of-the-art optimization-based inversion techniques, our solution not only yields superior performance across 8 editing methods but also achieves nearly an order of speed-up.
  arXiv  Detail & Related papers  (2023-10-02T18:01:55Z)
• LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance [0.0]
  LEDITS is a combined lightweight approach for real-image editing, incorporating the Edit Friendly DDPM inversion technique with Semantic Guidance. This approach achieves versatile edits, both subtle and extensive as well as alterations in composition and style, while requiring no optimization nor extensions to the architecture.
  arXiv  Detail & Related papers  (2023-07-02T09:11:09Z)
• LayerDiffusion: Layered Controlled Image Editing with Diffusion Models [5.58892860792971]
  LayerDiffusion is a semantic-based layered controlled image editing method. We leverage a large-scale text-to-image model and employ a layered controlled optimization strategy. Experimental results demonstrate the effectiveness of our method in generating highly coherent images.
  arXiv  Detail & Related papers  (2023-05-30T01:26:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.