{"url":"/task/open-domain-subject-to-video","name":"Open-Domain Subject-to-Video","slug":"open-domain-subject-to-video","description_markdown":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":6,"papers_with_code":6,"benchmarks":1,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/open-domain-subject-to-video-on-opens2v-eval","slug":"open-domain-subject-to-video-on-opens2v-eval","dataset":"OpenS2V-Eval","dataset_url":"/dataset/opens2v-eval","rows_in_archive":10,"metrics":["Total Score","Venue","Aesthetics","Motion","FaceSim","GmeScore","NexusScore","NaturalScore"],"first_row_in_archive_order":{"model":"Kling 1.6","paper_title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","paper_url":"/paper/identity-preserving-text-to-video-generation","paper_date":"2024-11-26","arxiv_id":"2411.17440","code_links":[{"title":"PKU-YuanGroup/ConsisID","url":"https://github.com/PKU-YuanGroup/ConsisID"}],"syntology":null}},{"leaderboard":null,"slug":"open-domain-subject-to-video-on","dataset":null,"dataset_url":null,"rows_in_archive":0,"metrics":["Total Score","Venue","Aesthetics","Motion","FaceSim","GmeScore","NexusScore","NaturalScore"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"open-domain-subject-to-video-on-opens2v-5m","dataset":"OpenS2V-5M","dataset_url":"/dataset/opens2v-5m","rows_in_archive":0,"metrics":["Total Score"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/coir","name":"CoIR","full_name":"Code Information Retrieval Benchmark","num_papers_in_archive":18},{"url":"/dataset/opens2v-eval","name":"OpenS2V-Eval","full_name":"","num_papers_in_archive":8},{"url":"/dataset/opens2v-5m","name":"OpenS2V-5M","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/image-to-video","name":"Image to Video Generation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":6,"of":6,"tagged_in_all":6,"items":[{"url":"/paper/opens2v-nexus-a-detailed-benchmark-and","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation","date":"2025-05-26","arxiv_id":"2505.20292","repositories_listed":2,"syntology":{"n":38,"n_ran":3,"n_unverified":35,"n_pointer_only":0}},{"url":"/paper/vace-all-in-one-video-creation-and-editing","title":"VACE: All-in-One Video Creation and Editing","date":"2025-03-10","arxiv_id":"2503.07598","repositories_listed":2,"syntology":{"n":19,"n_ran":8,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/magref-masked-guidance-for-any-reference","title":"MAGREF: Masked Guidance for Any-Reference Video Generation","date":"2025-05-29","arxiv_id":"2505.23742","repositories_listed":1,"syntology":{"n":14,"n_ran":5,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/skyreels-a2-compose-anything-in-video","title":"SkyReels-A2: Compose Anything in Video Diffusion Transformers","date":"2025-04-03","arxiv_id":"2504.02436","repositories_listed":1,"syntology":null},{"url":"/paper/phantom-subject-consistent-video-generation","title":"Phantom: Subject-consistent video generation via cross-modal alignment","date":"2025-02-16","arxiv_id":"2502.11079","repositories_listed":1,"syntology":{"n":12,"n_ran":3,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/identity-preserving-text-to-video-generation","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","date":"2024-11-26","arxiv_id":"2411.17440","repositories_listed":1,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}