{"url":"/dataset/dreambench","name":"DreamBooth","full_name":null,"description_markdown":"The **DreamBooth dataset** is a collection of images used for fine-tuning text-to-image diffusion models for subject-driven generation¹. Here are some key details about the dataset:\r\n\r\n- The dataset includes **30 subjects** from **15 different classes**¹.\r\n- Among these subjects, **9 are live subjects** (such as dogs and cats) and **21 are objects**¹.\r\n- The dataset contains a variable number of images per subject, typically between **4 to 6 images**¹.\r\n- Images of the subjects are usually captured in different conditions, environments, and under different angles¹.\r\n- The dataset also includes a file `prompts_and_classes.txt` which contains all of the prompts used in the paper for live subjects and objects, as well as the class name used for the subjects¹.\r\n- The images have either been captured by the paper authors or sourced from www.unsplash.com¹.\r\n- The `references_and_licenses.txt` file contains a list of all the reference links to the images in www.unsplash.com, along with the attribution to the photographer and the license of the image¹.\r\n\r\nThis dataset is part of the official repository for the Google paper \"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation\"¹. If you use this work, please cite the paper¹. Please note that this is not an officially supported Google product¹.\r\n\r\n(1) GitHub - google/dreambooth. https://github.com/google/dreambooth.\r\n(2) DreamBooth - Hugging Face. https://huggingface.co/docs/diffusers/training/dreambooth.\r\n(3) google/dreambooth · Datasets at Hugging Face. https://huggingface.co/datasets/google/dreambooth.\r\n(4) dreambooth: Mirror of https://huggingface.co/datasets/google .... https://gitee.com/hf-datasets/dreambooth.\r\n(5) undefined. https://github.com/huggingface/diffusers.\r\n(6) undefined. https://huggingface.co/datasets/google.","description_withheld":null,"homepage":"https://dreambooth.github.io","introduced_date":"2022-08-25","introduced_date_note":null,"introduced_by":{"paper":"/paper/dreambooth-fine-tuning-text-to-image","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","first_author":"Nataniel Ruiz","url":null},"license":null,"modalities":[],"tasks":[{"name":"Personalized Image Generation","url":"/task/personalized-image-generation","datasets_with_task":"/datasets/task/personalized-image-generation"}],"languages":[],"variants":["DreamBooth"],"data_loaders":[],"num_papers_in_archive":523,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/personalized-image-generation-on-dreambench","task":"Personalized Image Generation","dataset_variant":"DreamBooth","rows":7,"metrics":["Overall (CP * PF)","Concept Preservation (CP)","Prompt Following (PF)"],"first_row_in_archive_order":{"model":"DreamBooth LoRA SDXL v1.0","paper":"/paper/dreambooth-fine-tuning-text-to-image","metrics":{"Concept Preservation (CP)":"0.598","Overall (CP * PF)":"0.517","Prompt Following (PF)":"0.865"},"code_links":[{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/ppdiffusers/examples/dreambooth"},{"title":"XavierXiao/Dreambooth-Stable-Diffusion","url":"https://github.com/XavierXiao/Dreambooth-Stable-Diffusion"},{"title":"cloneofsimo/lora","url":"https://github.com/cloneofsimo/lora"},{"title":"showlab/Tune-A-Video","url":"https://github.com/showlab/Tune-A-Video"},{"title":"zrrskywalker/personalize-sam","url":"https://github.com/zrrskywalker/personalize-sam"},{"title":"google/dreambooth","url":"https://github.com/google/dreambooth"},{"title":"SnailDev/github-hot-hub","url":"https://github.com/SnailDev/github-hot-hub"},{"title":"lonnyzhang423/github-hot-hub","url":"https://github.com/lonnyzhang423/github-hot-hub"},{"title":"yandex-research/dvar","url":"https://github.com/yandex-research/dvar"},{"title":"csguoh/intlora","url":"https://github.com/csguoh/intlora"},{"title":"PrototypeNx/DETEX","url":"https://github.com/PrototypeNx/DETEX"},{"title":"jiahuadong/cifc","url":"https://github.com/jiahuadong/cifc"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/generative-multimodal-models-are-in-context","title":"Generative Multimodal Models are In-Context Learners","date":"2023-12-20","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ip-adapter-text-compatible-image-prompt","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","date":"2023-08-13","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":3,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/blip-diffusion-pre-trained-subject-1","title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing","date":"2023-05-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dreambooth-fine-tuning-text-to-image","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","date":"2022-08-25","rows_on_this_dataset":2,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":10,"samples_unverified":2,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/an-image-is-worth-one-word-personalizing-text","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","date":"2022-08-02","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":10,"samples_unverified":3,"pointer_only_for_licence":1,"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":4,"samples_harvested":37,"samples_ran":26,"samples_unverified":11,"pointer_only_for_licence":9,"papers_with_no_sample_that_ran":0,"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."}