{"url":"/sota/personalized-image-generation-on-dreambench","task":{"name":"Personalized Image Generation","url":"/task/personalized-image-generation","note":null},"dataset":{"name":"DreamBooth","url":"/dataset/dreambench"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Utilizes single or multiple images that contain the same subject or style, along with text prompt, to generate images that contain that subject as well as match the textual description. Includes finetuning-based methods (e.g. DreamBooth, Textual Inversion) as well as encoder-based methods (e.g. E4T, ELITE, and IP-Adapter, etc.).","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Overall (CP * PF)","Concept Preservation (CP)","Prompt Following (PF)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Overall (CP * PF)":null,"Concept Preservation (CP)":null,"Prompt Following (PF)":null}},"counts":{"rows":7,"rows_with_code":7,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"DreamBooth LoRA SDXL v1.0","metrics":{"Concept Preservation (CP)":"0.598","Overall (CP * PF)":"0.517","Prompt Following (PF)":"0.865"},"uses_additional_data":false,"paper_date":"2022-08-25","paper":"/paper/dreambooth-fine-tuning-text-to-image","paper_url":"https://arxiv.org/abs/2208.12242v2","paper_title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","code":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/ppdiffusers/examples/dreambooth","n_code_links":12,"syntology":{"n_ran":10,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":8}},{"rank_in_archive_order":2,"model":"IP-Adapter ViT-G SDXL v1.0","metrics":{"Concept Preservation (CP)":"0.593","Overall (CP * PF)":"0.380","Prompt Following (PF)":"0.640"},"uses_additional_data":false,"paper_date":"2023-08-13","paper":"/paper/ip-adapter-text-compatible-image-prompt","paper_url":"https://arxiv.org/abs/2308.06721v1","paper_title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","code":"https://github.com/tencent-ailab/ip-adapter","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"Emu2 SDXL v1.0","metrics":{"Concept Preservation (CP)":"0.528","Overall (CP * PF)":"0.364","Prompt Following (PF)":"0.690"},"uses_additional_data":false,"paper_date":"2023-12-20","paper":"/paper/generative-multimodal-models-are-in-context","paper_url":"https://arxiv.org/abs/2312.13286v2","paper_title":"Generative Multimodal Models are In-Context Learners","code":"https://github.com/baaivision/emu","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"DreamBooth SD v1.5","metrics":{"Concept Preservation (CP)":"0.494","Overall (CP * PF)":"0.356","Prompt Following (PF)":"0.721"},"uses_additional_data":false,"paper_date":"2022-08-25","paper":"/paper/dreambooth-fine-tuning-text-to-image","paper_url":"https://arxiv.org/abs/2208.12242v2","paper_title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","code":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/ppdiffusers/examples/dreambooth","n_code_links":12,"syntology":{"n_ran":10,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":8}},{"rank_in_archive_order":5,"model":"IP-Adapter-Plus ViT-H SDXL v1.0","metrics":{"Concept Preservation (CP)":"0.833","Overall (CP * PF)":"0.344","Prompt Following (PF)":"0.413"},"uses_additional_data":false,"paper_date":"2023-08-13","paper":"/paper/ip-adapter-text-compatible-image-prompt","paper_url":"https://arxiv.org/abs/2308.06721v1","paper_title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","code":"https://github.com/tencent-ailab/ip-adapter","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"BLIP-Diffusion SD v1.5","metrics":{"Concept Preservation (CP)":"0.547","Overall (CP * PF)":"0.271","Prompt Following (PF)":"0.495"},"uses_additional_data":false,"paper_date":"2023-05-24","paper":"/paper/blip-diffusion-pre-trained-subject-1","paper_url":"https://arxiv.org/abs/2305.14720v2","paper_title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing","code":"https://github.com/salesforce/lavis","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"Textual Inversion SD v1.5","metrics":{"Concept Preservation (CP)":"0.378","Overall (CP * PF)":"0.236","Prompt Following (PF)":"0.624"},"uses_additional_data":false,"paper_date":"2022-08-02","paper":"/paper/an-image-is-worth-one-word-personalizing-text","paper_url":"https://arxiv.org/abs/2208.01618v1","paper_title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","code":"https://github.com/cloneofsimo/lora","n_code_links":9,"syntology":{"n_ran":10,"n_unverified":3,"n_samples":13,"n_pointer_only_licence":1}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":6,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":26,"n_unverified":11,"n_samples":37,"n_pointer_only_licence":9,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":39,"n_unverified":18,"n_samples":57,"n_pointer_only_licence":17,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}