{"url":"/dataset/pie-bench","name":"PIE-Bench","full_name":"Prompt-based Image Editing Benchmark","description_markdown":"PIE-Bench comprises 700 images featuring 10 distinct editing types. Images are evenly distributed in natural and artificial scenes (e.g., paintings) among four categories: animal, human, indoor, and outdoor. Each image in PIE-Bench includes five annotations: source image prompt, target image prompt, editing instruction, main editing body, and the editing mask. Notably, the editing mask annotation (indicating the anticipated editing region) is crucial in accurate metrics computations as we expect the editing to only occur within a designated area.","description_withheld":null,"homepage":"https://github.com/cure-lab/DirectInversion","introduced_date":"2023-10-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/direct-inversion-boosting-diffusion-based","title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","first_author":"Xuan Ju","url":null},"license":{"name":"https://docs.google.com/document/d/1K7pjAgGwS8-lsA-D6Me4jAKmYszKpcyydiAEyZuTm2I/edit?usp=sharing","url":"https://docs.google.com/document/d/1K7pjAgGwS8-lsA-D6Me4jAKmYszKpcyydiAEyZuTm2I/edit?usp=sharing"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text-based Image Editing","url":"/task/text-based-image-editing","datasets_with_task":"/datasets/task/text-based-image-editing"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["PIE-Bench"],"data_loaders":[],"num_papers_in_archive":23,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-based-image-editing-on-pie-bench","task":"Text-based Image Editing","dataset_variant":"PIE-Bench","rows":18,"metrics":["Background PSNR","Background LPIPS","Structure Distance","CLIPSIM"],"first_row_in_archive_order":{"model":"KV-Edit","paper":"/paper/kv-edit-training-free-image-editing-for","metrics":{"Background LPIPS":"9.92","Background PSNR":"35.87","CLIPSIM":"25.63","Structure Distance":"1.98"},"code_links":[{"title":"Xilluill/KV-Edit","url":"https://github.com/Xilluill/KV-Edit"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/kv-edit-training-free-image-editing-for","title":"KV-Edit: Training-Free Image Editing for Precise Background Preservation","date":"2025-02-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":31,"samples_ran":15,"samples_unverified":16,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fireflow-fast-inversion-of-rectified-flow-for","title":"FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing","date":"2024-12-10","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":4,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/vision-guided-and-mask-enhanced-adaptive","title":"Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image Editing","date":"2024-10-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/inversion-free-image-editing-with-natural","title":"Inversion-Free Image Editing with Natural Language","date":"2023-12-07","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/direct-inversion-boosting-diffusion-based","title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","date":"2023-10-02","rows_on_this_dataset":4,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/negative-prompt-inversion-fast-image","title":"Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models","date":"2023-05-26","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":4,"samples_unverified":3,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/stylediffusion-prompt-embedding-inversion-for","title":"StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing","date":"2023-03-28","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/zero-shot-image-to-image-translation","title":"Zero-shot Image-to-Image Translation","date":"2023-02-06","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/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","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/null-text-inversion-for-editing-real-images","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","date":"2022-11-17","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/prompt-to-prompt-image-editing-with-cross","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","date":"2022-08-02","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":6,"samples_unverified":9,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":10,"samples_harvested":77,"samples_ran":37,"samples_unverified":40,"pointer_only_for_licence":12,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}