{"url":"/task/text-based-image-editing","name":"Text-based Image Editing","slug":"text-based-image-editing","description_markdown":"Nose should be sharped and lips should be less fat","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":45,"papers_with_code":29,"benchmarks":1,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":7,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/text-based-image-editing-on-pie-bench","slug":"text-based-image-editing-on-pie-bench","dataset":"PIE-Bench","dataset_url":"/dataset/pie-bench","rows_in_archive":18,"metrics":["Background PSNR","Background LPIPS","Structure Distance","CLIPSIM"],"first_row_in_archive_order":{"model":"KV-Edit","paper_title":"KV-Edit: Training-Free Image Editing for Precise Background Preservation","paper_url":"/paper/kv-edit-training-free-image-editing-for","paper_date":"2025-02-24","arxiv_id":"2502.17363","code_links":[{"title":"Xilluill/KV-Edit","url":"https://github.com/Xilluill/KV-Edit"}],"syntology":{"n":31,"n_ran":15,"n_unverified":16,"n_pointer_only":0}}},{"leaderboard":null,"slug":"text-based-image-editing-on-gedit-bench-en","dataset":"GEdit-Bench-EN","dataset_url":"/dataset/gedit-bench","rows_in_archive":0,"metrics":["Perceptual Quality"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/pie-bench","name":"PIE-Bench","full_name":"Prompt-based Image Editing Benchmark","num_papers_in_archive":23},{"url":"/dataset/imgedit-data","name":"ImgEdit-Data","full_name":"","num_papers_in_archive":10},{"url":"/dataset/gedit-bench","name":"GEdit-Bench-EN","full_name":"","num_papers_in_archive":6},{"url":"/dataset/imgedit","name":"ImgEdit","full_name":"","num_papers_in_archive":4},{"url":"/dataset/oir-bench","name":"OIR-Bench","full_name":"","num_papers_in_archive":1},{"url":"/dataset/manicups","name":"ManiCups","full_name":"ManiCups","num_papers_in_archive":0},{"url":"/dataset/nhr-edit","name":"NHR-Edit","full_name":"NoHumansRequired Edit Dataset","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/text-to-image-generation","name":"Text-to-Image Generation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":29,"of":29,"tagged_in_all":45,"items":[{"url":"/paper/prompt-to-prompt-image-editing-with-cross","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","date":"2022-08-02","arxiv_id":"2208.01626","repositories_listed":7,"syntology":{"n":15,"n_ran":6,"n_unverified":9,"n_pointer_only":3}},{"url":"/paper/instructpix2pix-learning-to-follow-image","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","date":"2022-11-17","arxiv_id":"2211.09800","repositories_listed":6,"syntology":{"n":20,"n_ran":15,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/differential-diffusion-giving-each-pixel-its","title":"Differential Diffusion: Giving Each Pixel Its Strength","date":"2023-06-01","arxiv_id":"2306.00950","repositories_listed":4,"syntology":null},{"url":"/paper/masactrl-tuning-free-mutual-self-attention","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","date":"2023-04-17","arxiv_id":"2304.08465","repositories_listed":4,"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/plug-and-play-diffusion-features-for-text","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","date":"2022-11-22","arxiv_id":"2211.12572","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/null-text-inversion-for-editing-real-images","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","date":"2022-11-17","arxiv_id":"2211.09794","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/direct-inversion-boosting-diffusion-based","title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","date":"2023-10-02","arxiv_id":"2310.01506","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":6}},{"url":"/paper/versatile-diffusion-text-images-and","title":"Versatile Diffusion: Text, Images and Variations All in One Diffusion Model","date":"2022-11-15","arxiv_id":"2211.08332","repositories_listed":3,"syntology":null},{"url":"/paper/lance-stress-testing-visual-models-by-1","title":"LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images","date":"2023-05-30","arxiv_id":"2305.19164","repositories_listed":2,"syntology":{"n":10,"n_ran":3,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/erasing-concepts-from-diffusion-models","title":"Erasing Concepts from Diffusion Models","date":"2023-03-13","arxiv_id":"2303.07345","repositories_listed":2,"syntology":{"n":8,"n_ran":4,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/zero-shot-image-to-image-translation","title":"Zero-shot Image-to-Image Translation","date":"2023-02-06","arxiv_id":"2302.03027","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/edict-exact-diffusion-inversion-via-coupled","title":"EDICT: Exact Diffusion Inversion via Coupled Transformations","date":"2022-11-22","arxiv_id":"2211.12446","repositories_listed":2,"syntology":null},{"url":"/paper/cora-correspondence-aware-image-editing-using","title":"Cora: Correspondence-aware image editing using few step diffusion","date":"2025-05-29","arxiv_id":"2505.23907","repositories_listed":1,"syntology":null},{"url":"/paper/illume-illuminating-unified-mllm-with-dual","title":"ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement","date":"2025-04-02","arxiv_id":"2504.01934","repositories_listed":1,"syntology":{"n":20,"n_ran":4,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/kv-edit-training-free-image-editing-for","title":"KV-Edit: Training-Free Image Editing for Precise Background Preservation","date":"2025-02-24","arxiv_id":"2502.17363","repositories_listed":1,"syntology":{"n":31,"n_ran":15,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/fireflow-fast-inversion-of-rectified-flow-for","title":"FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing","date":"2024-12-10","arxiv_id":"2412.07517","repositories_listed":1,"syntology":{"n":11,"n_ran":4,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/stable-flow-vital-layers-for-training-free","title":"Stable Flow: Vital Layers for Training-Free Image Editing","date":"2024-11-21","arxiv_id":"2411.14430","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":5}},{"url":"/paper/vision-guided-and-mask-enhanced-adaptive","title":"Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image Editing","date":"2024-10-14","arxiv_id":"2410.10496","repositories_listed":1,"syntology":null},{"url":"/paper/flexiedit-frequency-aware-latent-refinement","title":"FlexiEdit: Frequency-Aware Latent Refinement for Enhanced Non-Rigid Editing","date":"2024-07-25","arxiv_id":"2407.17850","repositories_listed":1,"syntology":{"n":20,"n_ran":11,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/paint-by-inpaint-learning-to-add-image","title":"Paint by Inpaint: Learning to Add Image Objects by Removing Them First","date":"2024-04-28","arxiv_id":"2404.18212","repositories_listed":1,"syntology":null},{"url":"/paper/doubly-abductive-counterfactual-inference-for","title":"Doubly Abductive Counterfactual Inference for Text-based Image Editing","date":"2024-03-05","arxiv_id":"2403.02981","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/specref-a-fast-training-free-baseline-of","title":"SpecRef: A Fast Training-free Baseline of Specific Reference-Condition Real Image Editing","date":"2024-01-07","arxiv_id":"2401.03433","repositories_listed":1,"syntology":null},{"url":"/paper/inversion-free-image-editing-with-natural","title":"Inversion-Free Image Editing with Natural Language","date":"2023-12-07","arxiv_id":"2312.04965","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/dynamic-prompt-learning-addressing-cross-1","title":"Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing","date":"2023-09-27","arxiv_id":"2309.15664","repositories_listed":1,"syntology":null},{"url":"/paper/controlling-geometric-abstraction-and-texture","title":"Controlling Geometric Abstraction and Texture for Artistic Images","date":"2023-07-31","arxiv_id":"2308.00148","repositories_listed":1,"syntology":null},{"url":"/paper/stylediffusion-prompt-embedding-inversion-for","title":"StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing","date":"2023-03-28","arxiv_id":"2303.15649","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/svdiff-compact-parameter-space-for-diffusion","title":"SVDiff: Compact Parameter Space for Diffusion Fine-Tuning","date":"2023-03-20","arxiv_id":"2303.11305","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/hive-harnessing-human-feedback-for","title":"HIVE: Harnessing Human Feedback for Instructional Visual Editing","date":"2023-03-16","arxiv_id":"2303.09618","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/maniclip-multi-attribute-face-manipulation","title":"ManiCLIP: Multi-Attribute Face Manipulation from Text","date":"2022-10-02","arxiv_id":"2210.00445","repositories_listed":1,"syntology":null}],"syntology_records":19,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}