Browse State-of-the-Art › Text-based Image Editing
Text-based Image Editing
29 papers with code · 1 benchmark · 7 datasets archive 2025-07-28
Nose should be sharped and lips should be less fat
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 2 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): PIE-Bench (2 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| PIE-Bench (18 rows) | KV-Edit | KV-Edit: Training-Free Image Editing for Precise Background Preservation | code | Syntology official (archive's flag): 16 ran · 16 ran (of which 12 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 15 unverified | Compare |
| GEdit-Bench-EN (0 rows) | no rows in the archive | — | — | ||
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. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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
Papers archive 2025-07-28
archive papers tagged: 45 · with a code link: 29 · where Syntology ran a sample: 19 (17 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (19 of 45 tagged: 17 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 45 of 45, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
2 Aug 2022 7 repositories listed Syntology official: harvested, nothing ran · 9 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified (of 15 harvested samples) · 4 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…
-
17 Nov 2022 6 repositories listed Syntology community repositories only · 17 ran (of which 2 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 5 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified (of 20 harvested samples) · 4 pointer-only (licence)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.
-
1 Jun 2023 4 repositories listedWhile 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.
-
17 Apr 2023 4 repositories listed Syntology official (archive's flag): 1 ran · 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 4 samples that ran constructed an object rather than computing a result (of 7 harvested samples) · 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.
-
22 Nov 2022 4 repositories listed Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)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.
-
17 Nov 2022 4 repositories listed Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)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.
-
2 Oct 2023 3 repositories listed Syntology official (archive's flag): 3 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples) · 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…
-
15 Nov 2022 3 repositories listedIn 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…
-
30 May 2023 2 repositories listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 10 harvested samples) · 4 pointer-only (licence)We propose an automated algorithm to stress-test a trained visual model by generating language-guided counterfactual test images (LANCE).
-
13 Mar 2023 2 repositories listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified (of 8 harvested samples)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.
-
6 Feb 2023 2 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)However, it is still challenging to directly apply these models for editing real images for two reasons.
-
22 Nov 2022 2 repositories listedEDICT 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.
-
29 May 2025 1 repository listedHowever, edits requiring significant structural changes, such as non-rigid deformations, object modifications, or content generation, remain challenging.
-
2 Apr 2025 1 repository listed Syntology 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 20 harvested samples)We present ILLUME+ that leverages dual visual tokenization and a diffusion decoder to improve both deep semantic understanding and high-fidelity image generation.
-
24 Feb 2025 1 repository listed Syntology official (archive's flag): 16 ran · 16 ran (of which 12 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 15 unverified (of 31 harvested samples)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…
-
10 Dec 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified (of 11 harvested samples)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.
-
21 Nov 2024 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 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.
-
14 Oct 2024 1 repository listedDespite 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…
-
25 Jul 2024 1 repository listed Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified (of 20 harvested samples)Current image editing methods primarily utilize DDIM Inversion, employing a two-branch diffusion approach to preserve the attributes and layout of the original image.
-
28 Apr 2024 1 repository listedWe 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…
-
5 Mar 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 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…
-
7 Jan 2024 1 repository listedTo 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…
-
7 Dec 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 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.
-
27 Sep 2023 1 repository listedLarge-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.
-
31 Jul 2023 1 repository listedWe present a novel method for the interactive control of geometric abstraction and texture in artistic images.
-
28 Mar 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images.
-
20 Mar 2023 1 repository listed Syntology 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample)Diffusion models have achieved remarkable success in text-to-image generation, enabling the creation of high-quality images from text prompts or other modalities.
-
16 Mar 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 2 pointer-only (licence)Incorporating human feedback has been shown to be crucial to align text generated by large language models to human preferences.
-
2 Oct 2022 1 repository listedIn this paper we present a novel multi-attribute face manipulation method based on textual descriptions.
-
18 Jul 2025 0 repositories listedRecent advances in generative modeling enable image editing assistants that follow natural language instructions without additional user input.
-
10 Apr 2025 0 repositories listed
-
PartEdit: Fine-Grained Image Editing using Pre-Trained Diffusion Models6 Feb 2025 0 repositories listed
-
FeedEdit: Text-Based Image Editing with Dynamic Feedback Regulation1 Jan 2025 0 repositories listed
-
Action-based image editing guided by human instructions5 Dec 2024 0 repositories listed
-
LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Pair28 Nov 2024 0 repositories listed
-
Pathways on the Image Manifold: Image Editing via Video Generation25 Nov 2024 0 repositories listed
-
Pixel Is Not A Barrier: An Effective Evasion Attack for Pixel-Domain Diffusion Models21 Aug 2024 0 repositories listed
-
TurboEdit: Instant text-based image editing14 Aug 2024 0 repositories listed
-
Specify and Edit: Overcoming Ambiguity in Text-Based Image Editing29 Jul 2024 0 repositories listed
-
TIE: Revolutionizing Text-based Image Editing for Complex-Prompt Following and High-Fidelity Editing27 May 2024 0 repositories listed
-
E4C: Enhance Editability for Text-Based Image Editing by Harnessing Efficient CLIP Guidance15 Mar 2024 0 repositories listed
-
Minecraft-ify: Minecraft Style Image Generation with Text-guided Image Editing for In-Game Application8 Feb 2024 0 repositories listed
-
Wavelet-Guided Acceleration of Text Inversion in Diffusion-Based Image Editing18 Jan 2024 0 repositories listed
-
26 May 2023 0 repositories listed
-
Delta Denoising Score14 Apr 2023 0 repositories listed
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; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections