{"url":"/dataset/dreambooth","name":"DreamBooth++","full_name":null,"description_markdown":"DreamBench++ is a human-aligned benchmark for personalized image generation¹. It's automated by advanced multimodal GPT models¹. The goal of DreamBench++ is to assist humans in everyday work and life by creatively generating personalized content¹².\r\n\r\nHere are some key features of DreamBench++:\r\n- **Prompts Design**: The prompts are systematically designed to let GPT be both human-aligned and self-aligned¹.\r\n- **Task Reinforcement**: The GPT models are empowered with task reinforcement¹.\r\n- **Diverse Dataset**: A comprehensive dataset comprising diverse images and prompts is constructed¹.\r\n- **Human-Aligned Evaluation**: By benchmarking 7 modern generative models, DreamBench++ results in significantly more human-aligned evaluation¹.\r\n\r\n(1) DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation. https://dreambenchplus.github.io/.\r\n(2) DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation. https://arxiv.org/abs/2406.16855.\r\n(3) 图像生成评估基准DREAMBENCH++：与人类偏好对齐的 .... https://sd114.wiki/2676.html.\r\n(4) DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation. https://arxiv.org/html/2406.16855v1.","description_withheld":null,"homepage":"https://dreambenchplus.github.io","introduced_date":"2024-06-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/dreambench-a-human-aligned-benchmark-for","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","first_author":"Yuang Peng","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["DreamBooth++"],"data_loaders":[],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"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."}