Text-based Image Editing

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

2 leaderboard tables shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

7 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

29 shown of 29 papers with code (45 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Prompt-to-Prompt Image Editing with Cross Attention Control
  2 Aug 2022 7 repositories listed Syntology ran 6 of 15 samples · 9 unverified · 3 pointer-only (licence)
  Editing is challenging for these generative models, since an innate property of an editing technique is to preserve most of the original image, while in the text-based models, even a small modification of the text…
• InstructPix2Pix: Learning to Follow Image Editing Instructions
  17 Nov 2022 6 repositories listed Syntology ran 15 of 20 samples · 5 unverified
  We propose a method for editing images from human instructions: given an input image and a written instruction that tells the model what to do, our model follows these instructions to edit the image.
• Differential Diffusion: Giving Each Pixel Its Strength
  1 Jun 2023 4 repositories listed
  While current techniques enable user control over the degree of change in an image edit, the controllability is limited to global changes over an entire edited region.
• MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing
  17 Apr 2023 4 repositories listed Syntology ran 4 of 7 samples · 3 unverified · 1 pointer-only (licence)
  Despite the success in large-scale text-to-image generation and text-conditioned image editing, existing methods still struggle to produce consistent generation and editing results.
• Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
  22 Nov 2022 4 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  Large-scale text-to-image generative models have been a revolutionary breakthrough in the evolution of generative AI, allowing us to synthesize diverse images that convey highly complex visual concepts.
• Null-text Inversion for Editing Real Images using Guided Diffusion Models
  17 Nov 2022 4 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  Our Null-text inversion, based on the publicly available Stable Diffusion model, is extensively evaluated on a variety of images and prompt editing, showing high-fidelity editing of real images.
• Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
  2 Oct 2023 3 repositories listed Syntology ran 4 of 6 samples · 2 unverified · 6 pointer-only (licence)
  Specifically, in the context of diffusion-based editing, where a source image is edited according to a target prompt, the process commences by acquiring a noisy latent vector corresponding to the source image via the…
• Versatile Diffusion: Text, Images and Variations All in One Diffusion Model
  15 Nov 2022 3 repositories listed
  In this work, we expand the existing single-flow diffusion pipeline into a multi-task multimodal network, dubbed Versatile Diffusion (VD), that handles multiple flows of text-to-image, image-to-text, and variations in…
• LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images
  30 May 2023 2 repositories listed Syntology ran 3 of 10 samples · 7 unverified
  We propose an automated algorithm to stress-test a trained visual model by generating language-guided counterfactual test images (LANCE).
• Erasing Concepts from Diffusion Models
  13 Mar 2023 2 repositories listed Syntology ran 4 of 8 samples · 4 unverified
  We propose a fine-tuning method that can erase a visual concept from a pre-trained diffusion model, given only the name of the style and using negative guidance as a teacher.
• Zero-shot Image-to-Image Translation
  6 Feb 2023 2 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  However, it is still challenging to directly apply these models for editing real images for two reasons.
• EDICT: Exact Diffusion Inversion via Coupled Transformations
  22 Nov 2022 2 repositories listed
  EDICT enables mathematically exact inversion of real and model-generated images by maintaining two coupled noise vectors which are used to invert each other in an alternating fashion.
• Cora: Correspondence-aware image editing using few step diffusion
  29 May 2025 1 repository listed
  However, edits requiring significant structural changes, such as non-rigid deformations, object modifications, or content generation, remain challenging.
• ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement
  2 Apr 2025 1 repository listed Syntology ran 4 of 20 samples · 16 unverified
  We present ILLUME+ that leverages dual visual tokenization and a diffusion decoder to improve both deep semantic understanding and high-fidelity image generation.
• KV-Edit: Training-Free Image Editing for Precise Background Preservation
  24 Feb 2025 1 repository listed Syntology ran 15 of 31 samples · 16 unverified
  Here, we propose KV-Edit, a training-free approach that uses KV cache in DiTs to maintain background consistency, where background tokens are preserved rather than regenerated, eliminating the need for complex…
• FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing
  10 Dec 2024 1 repository listed Syntology ran 4 of 11 samples · 7 unverified
  Though Rectified Flows (ReFlows) with distillation offers a promising way for fast sampling, its fast inversion transforms images back to structured noise for recovery and following editing remains unsolved.
• Stable Flow: Vital Layers for Training-Free Image Editing
  21 Nov 2024 1 repository listed Syntology ran 2 of 5 samples · 3 unverified · 5 pointer-only (licence)
  The main challenge is that, unlike the UNet-based models, DiT lacks a coarse-to-fine synthesis structure, making it unclear in which layers to perform the injection.
• Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image Editing
  14 Oct 2024 1 repository listed
  Despite their advances, existing methods still encounter three key issues: 1) limited capacity of the text prompt in guiding target image generation, 2) insufficient mining of word-to-patch and patch-to-patch…
• FlexiEdit: Frequency-Aware Latent Refinement for Enhanced Non-Rigid Editing
  25 Jul 2024 1 repository listed Syntology ran 11 of 20 samples · 9 unverified
  Current image editing methods primarily utilize DDIM Inversion, employing a two-branch diffusion approach to preserve the attributes and layout of the original image.
• Paint by Inpaint: Learning to Add Image Objects by Removing Them First
  28 Apr 2024 1 repository listed
  We address this by leveraging the insight that removing objects (Inpaint) is significantly simpler than its inverse process of adding them (Paint), attributed to the utilization of segmentation mask datasets alongside…
• Doubly Abductive Counterfactual Inference for Text-based Image Editing
  5 Mar 2024 1 repository listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  Through the lens of the formulation, we find that the crux of TBIE is that existing techniques hardly achieve a good trade-off between editability and fidelity, mainly due to the overfitting of the single-image…
• SpecRef: A Fast Training-free Baseline of Specific Reference-Condition Real Image Editing
  7 Jan 2024 1 repository listed
  To increase user freedom, we propose a new task called Specific Reference Condition Real Image Editing, which allows user to provide a reference image to further control the outcome, such as replacing an object with a…
• Inversion-Free Image Editing with Natural Language
  7 Dec 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  We show that when the initial sample is known, a special variance schedule reduces the denoising step to the same form as the multi-step consistency sampling.
• Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing
  27 Sep 2023 1 repository listed
  Large-scale text-to-image generative models have been a ground-breaking development in generative AI, with diffusion models showing their astounding ability to synthesize convincing images following an input text prompt.
• Controlling Geometric Abstraction and Texture for Artistic Images
  31 Jul 2023 1 repository listed
  We present a novel method for the interactive control of geometric abstraction and texture in artistic images.
• StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing
  28 Mar 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images.
• SVDiff: Compact Parameter Space for Diffusion Fine-Tuning
  20 Mar 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  Diffusion models have achieved remarkable success in text-to-image generation, enabling the creation of high-quality images from text prompts or other modalities.
• HIVE: Harnessing Human Feedback for Instructional Visual Editing
  16 Mar 2023 1 repository listed Syntology ran 3 of 4 samples · 1 unverified
  Incorporating human feedback has been shown to be crucial to align text generated by large language models to human preferences.
• ManiCLIP: Multi-Attribute Face Manipulation from Text
  2 Oct 2022 1 repository listed
  In this paper we present a novel multi-attribute face manipulation method based on textual descriptions.

Syntology lines on 19 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.