{"url":"/dataset/storybench","name":"StoryBench","full_name":"StoryBench: A Multifaceted Benchmark for Continuous Story Visualization","description_markdown":"StoryBench is a multi-task benchmark to reliably evaluate the ability of text-to-video models to generate stories from a sequence of captions and their duration. It includes three datasets (DiDeMo, Oops, UVO) and three video generation tasks of increasing difficulty: action execution, where the next action must be generated starting from a conditioning video; story continuation, where a sequence of actions must be executed starting from a conditioning video; and story generation, where a video must be generated from only text prompts.","description_withheld":null,"homepage":"https://github.com/google/storybench","introduced_date":"2023-08-22","introduced_date_note":null,"introduced_by":null,"license":{"name":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Story Visualization","url":"/task/story-visualization","datasets_with_task":"/datasets/task/story-visualization"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["StoryBench","DiDeMo-CSV","Zero-Shot Action Execution DiDeMO-CSV"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/story-visualization-on-zero-shot-action","task":"Story Visualization","dataset_variant":"Zero-Shot Action Execution DiDeMO-CSV","rows":1,"metrics":["FID_Iv3","FVD_I3D","SIM_Iv3","PQA","VTM_CLIP","FID_CLIP","FVD_IV","SIM_CLIP","VTM_IV"],"first_row_in_archive_order":{"model":"Phenaki-Gen","paper":null,"metrics":{"FID_CLIP":"97.2±0.34","FID_Iv3":"195±1.57","FVD_I3D":"454±3.21","FVD_IV":"78.0±0.25","PQA":"6.7±0.02","SIM_CLIP":"64.3±0.08","SIM_Iv3":"70.7±0.03","VTM_CLIP":"22.1±0.02","VTM_IV":"22.9±0.05"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+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."}