{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/text-to-video-generation/papers/ran/1","list_of":"/task/text-to-video-generation","task":"Text-to-Video Generation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,45],"of":45,"counts":{"archive_papers_tagged":201,"with_a_code_link":97,"where_syntology_ran_a_sample":45,"not_listed_spam_title":0,"listed":201,"listed_where_code_ran":45,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":43,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":43,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/text-to-video-generation/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/flashvideo-flowing-fidelity-to-detail-for","slug":"flashvideo-flowing-fidelity-to-detail-for","title":"FlashVideo:Flowing Fidelity to Detail for Efficient High-Resolution Video Generation","date":"2025-02-07","arxiv_id":"2502.05179","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":3,"n_no_contract":8,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 3 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/flashvideo-flowing-fidelity-to-detail-for#ran","syntology_url":"https://syntology.ai/paper/2502.05179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05179"}},"official":{"repos":["foundationvision/flashvideo"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/vchitect-2-0-parallel-transformer-for-scaling","slug":"vchitect-2-0-parallel-transformer-for-scaling","title":"Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models","date":"2025-01-14","arxiv_id":"2501.08453","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vchitect-2-0-parallel-transformer-for-scaling#ran","syntology_url":"https://syntology.ai/paper/2501.08453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.08453"}},"official":null}},{"url":"/paper/open-sora-democratizing-efficient-video","slug":"open-sora-democratizing-efficient-video","title":"Open-Sora: Democratizing Efficient Video Production for All","date":"2024-12-29","arxiv_id":"2412.20404","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/open-sora-democratizing-efficient-video#ran","syntology_url":"https://syntology.ai/paper/2412.20404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.20404"}},"official":{"repos":["hpcaitech/open-sora"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/generate-any-scene-evaluating-and-improving","slug":"generate-any-scene-evaluating-and-improving","title":"Generate Any Scene: Evaluating and Improving Text-to-Vision Generation with Scene Graph Programming","date":"2024-12-11","arxiv_id":"2412.08221","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":1,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/generate-any-scene-evaluating-and-improving#ran","syntology_url":"https://syntology.ai/paper/2412.08221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.08221"}},"official":{"repos":["RAIVNLab/GenerateAnyScene"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/phyt2v-llm-guided-iterative-self-refinement","slug":"phyt2v-llm-guided-iterative-self-refinement","title":"PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation","date":"2024-11-30","arxiv_id":"2412.00596","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":16,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/phyt2v-llm-guided-iterative-self-refinement#ran","syntology_url":"https://syntology.ai/paper/2412.00596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.00596"}},"official":{"repos":["pittisl/phyt2v"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-motion-in-text-to-video-generation","slug":"enhancing-motion-in-text-to-video-generation","title":"Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning","date":"2024-10-31","arxiv_id":"2410.24219","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/enhancing-motion-in-text-to-video-generation#ran","syntology_url":"https://syntology.ai/paper/2410.24219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.24219"}},"official":{"repos":["pr-ryan/demo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/motionaura-generating-high-quality-and-motion","slug":"motionaura-generating-high-quality-and-motion","title":"MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion","date":"2024-10-10","arxiv_id":"2410.07659","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/motionaura-generating-high-quality-and-motion#ran","syntology_url":"https://syntology.ai/paper/2410.07659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07659"}},"official":{"repos":["CandleLabAI/MotionAura-ICLR-2025"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pyramidal-flow-matching-for-efficient-video","slug":"pyramidal-flow-matching-for-efficient-video","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","date":"2024-10-08","arxiv_id":"2410.05954","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/pyramidal-flow-matching-for-efficient-video#ran","syntology_url":"https://syntology.ai/paper/2410.05954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05954"}},"official":{"repos":["jy0205/Pyramid-Flow"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cogvideox-text-to-video-diffusion-models-with","slug":"cogvideox-text-to-video-diffusion-models-with","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","date":"2024-08-12","arxiv_id":"2408.06072","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cogvideox-text-to-video-diffusion-models-with#ran","syntology_url":"https://syntology.ai/paper/2408.06072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06072"}},"official":{"repos":["thudm/cogvideo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mmtrail-a-multimodal-trailer-video-dataset","slug":"mmtrail-a-multimodal-trailer-video-dataset","title":"MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions","date":"2024-07-30","arxiv_id":"2407.20962","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mmtrail-a-multimodal-trailer-video-dataset#ran","syntology_url":"https://syntology.ai/paper/2407.20962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.20962"}},"official":{"repos":["litwellchi/mmtrail"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/t2v-compbench-a-comprehensive-benchmark-for","slug":"t2v-compbench-a-comprehensive-benchmark-for","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","date":"2024-07-19","arxiv_id":"2407.14505","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/t2v-compbench-a-comprehensive-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2407.14505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14505"}},"official":{"repos":["KaiyueSun98/T2V-CompBench"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluation-of-text-to-video-generation-models","slug":"evaluation-of-text-to-video-generation-models","title":"Evaluation of Text-to-Video Generation Models: A Dynamics Perspective","date":"2024-07-01","arxiv_id":"2407.01094","repositories_listed":1,"syntology":{"n":21,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":21,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/evaluation-of-text-to-video-generation-models#ran","syntology_url":"https://syntology.ai/paper/2407.01094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01094"}},"official":{"repos":["mingxiangl/devil"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/chronomagic-bench-a-benchmark-for-metamorphic","slug":"chronomagic-bench-a-benchmark-for-metamorphic","title":"ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation","date":"2024-06-26","arxiv_id":"2406.18522","repositories_listed":2,"syntology":{"n":27,"n_ran":24,"n_constructed":0,"n_ran_checked":21,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":19,"n_pointer_only":0,"phrase":"24 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 1 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/chronomagic-bench-a-benchmark-for-metamorphic#ran","syntology_url":"https://syntology.ai/paper/2406.18522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18522"}},"official":{"repos":["pku-yuangroup/chronomagic-bench","pku-yuangroup/magictime"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":0,"n_ran_no_instrument_failure":20,"n_unverified":3,"ran_from_kinds":["community","official"]}}},{"url":"/paper/motionclone-training-free-motion-cloning-for","slug":"motionclone-training-free-motion-cloning-for","title":"MotionClone: Training-Free Motion Cloning for Controllable Video Generation","date":"2024-06-08","arxiv_id":"2406.05338","repositories_listed":2,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":15,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/motionclone-training-free-motion-cloning-for#ran","syntology_url":"https://syntology.ai/paper/2406.05338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05338"}},"official":{"repos":["bujiazi/motionclone","lpengyang/motionclone"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/videotetris-towards-compositional-text-to","slug":"videotetris-towards-compositional-text-to","title":"VideoTetris: Towards Compositional Text-to-Video Generation","date":"2024-06-06","arxiv_id":"2406.04277","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/videotetris-towards-compositional-text-to#ran","syntology_url":"https://syntology.ai/paper/2406.04277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04277"}},"official":{"repos":["yangling0818/videotetris"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/fifo-diffusion-generating-infinite-videos","slug":"fifo-diffusion-generating-infinite-videos","title":"FIFO-Diffusion: Generating Infinite Videos from Text without Training","date":"2024-05-19","arxiv_id":"2405.11473","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":6,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/fifo-diffusion-generating-infinite-videos#ran","syntology_url":"https://syntology.ai/paper/2405.11473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11473"}},"official":{"repos":["jjihwan/FIFO-Diffusion_public"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/cameractrl-enabling-camera-control-for-text","slug":"cameractrl-enabling-camera-control-for-text","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","date":"2024-04-02","arxiv_id":"2404.02101","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cameractrl-enabling-camera-control-for-text#ran","syntology_url":"https://syntology.ai/paper/2404.02101","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02101"}},"official":{"repos":["hehao13/cameractrl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/streamingt2v-consistent-dynamic-and","slug":"streamingt2v-consistent-dynamic-and","title":"StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text","date":"2024-03-21","arxiv_id":"2403.14773","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/streamingt2v-consistent-dynamic-and#ran","syntology_url":"https://syntology.ai/paper/2403.14773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14773"}},"official":{"repos":["picsart-ai-research/streamingt2v"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mora-enabling-generalist-video-generation-via","slug":"mora-enabling-generalist-video-generation-via","title":"Mora: Enabling Generalist Video Generation via A Multi-Agent Framework","date":"2024-03-20","arxiv_id":"2403.13248","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mora-enabling-generalist-video-generation-via#ran","syntology_url":"https://syntology.ai/paper/2403.13248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13248"}},"official":{"repos":["lichao-sun/mora"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vstar-generative-temporal-nursing-for-longer","slug":"vstar-generative-temporal-nursing-for-longer","title":"VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis","date":"2024-03-20","arxiv_id":"2403.13501","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":2,"n_honours":2,"n_violates":3,"n_no_contract":4,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 3 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/vstar-generative-temporal-nursing-for-longer#ran","syntology_url":"https://syntology.ai/paper/2403.13501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13501"}},"official":{"repos":["boschresearch/VSTAR"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/vidprom-a-million-scale-real-prompt-gallery","slug":"vidprom-a-million-scale-real-prompt-gallery","title":"VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models","date":"2024-03-10","arxiv_id":"2403.06098","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vidprom-a-million-scale-real-prompt-gallery#ran","syntology_url":"https://syntology.ai/paper/2403.06098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06098"}},"official":{"repos":["wangwenhao0716/vidprom"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/video-lavit-unified-video-language-pre","slug":"video-lavit-unified-video-language-pre","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","date":"2024-02-05","arxiv_id":"2402.03161","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/video-lavit-unified-video-language-pre#ran","syntology_url":"https://syntology.ai/paper/2402.03161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03161"}},"official":null}},{"url":"/paper/lumiere-a-space-time-diffusion-model-for","slug":"lumiere-a-space-time-diffusion-model-for","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","date":"2024-01-23","arxiv_id":"2401.12945","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lumiere-a-space-time-diffusion-model-for#ran","syntology_url":"https://syntology.ai/paper/2401.12945","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12945"}},"official":null}},{"url":"/paper/videocrafter2-overcoming-data-limitations-for","slug":"videocrafter2-overcoming-data-limitations-for","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","date":"2024-01-17","arxiv_id":"2401.09047","repositories_listed":2,"syntology":{"n":21,"n_ran":15,"n_constructed":1,"n_ran_checked":11,"n_instrument":4,"n_unverified":6,"n_honours":3,"n_violates":3,"n_no_contract":5,"n_pointer_only":21,"phrase":"15 ran (of which 1 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 3 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/videocrafter2-overcoming-data-limitations-for#ran","syntology_url":"https://syntology.ai/paper/2401.09047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09047"}},"official":{"repos":["ailab-cvc/videocrafter"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/latte-latent-diffusion-transformer-for-video","slug":"latte-latent-diffusion-transformer-for-video","title":"Latte: Latent Diffusion Transformer for Video Generation","date":"2024-01-05","arxiv_id":"2401.03048","repositories_listed":4,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/latte-latent-diffusion-transformer-for-video#ran","syntology_url":"https://syntology.ai/paper/2401.03048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03048"}},"official":{"repos":["maxin-cn/Latte"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/peekaboo-interactive-video-generation-via","slug":"peekaboo-interactive-video-generation-via","title":"PEEKABOO: Interactive Video Generation via Masked-Diffusion","date":"2023-12-12","arxiv_id":"2312.07509","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/peekaboo-interactive-video-generation-via#ran","syntology_url":"https://syntology.ai/paper/2312.07509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07509"}},"official":{"repos":["microsoft/peekaboo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/freeinit-bridging-initialization-gap-in-video","slug":"freeinit-bridging-initialization-gap-in-video","title":"FreeInit: Bridging Initialization Gap in Video Diffusion Models","date":"2023-12-12","arxiv_id":"2312.07537","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/freeinit-bridging-initialization-gap-in-video#ran","syntology_url":"https://syntology.ai/paper/2312.07537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07537"}},"official":{"repos":["tianxingwu/freeinit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/stylecrafter-enhancing-stylized-text-to-video","slug":"stylecrafter-enhancing-stylized-text-to-video","title":"StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter","date":"2023-12-01","arxiv_id":"2312.00330","repositories_listed":3,"syntology":{"n":23,"n_ran":17,"n_constructed":0,"n_ran_checked":14,"n_instrument":3,"n_unverified":6,"n_honours":3,"n_violates":3,"n_no_contract":8,"n_pointer_only":7,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 3 honoured, 3 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/stylecrafter-enhancing-stylized-text-to-video#ran","syntology_url":"https://syntology.ai/paper/2312.00330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00330"}},"official":{"repos":["GongyeLiu/StyleCrafter"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/videocrafter1-open-diffusion-models-for-high","slug":"videocrafter1-open-diffusion-models-for-high","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","date":"2023-10-30","arxiv_id":"2310.19512","repositories_listed":3,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":7,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/videocrafter1-open-diffusion-models-for-high#ran","syntology_url":"https://syntology.ai/paper/2310.19512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19512"}},"official":{"repos":["ailab-cvc/videocrafter"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/evalcrafter-benchmarking-and-evaluating-large","slug":"evalcrafter-benchmarking-and-evaluating-large","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","date":"2023-10-17","arxiv_id":"2310.11440","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/evalcrafter-benchmarking-and-evaluating-large#ran","syntology_url":"https://syntology.ai/paper/2310.11440","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.11440"}},"official":{"repos":["EvalCrafter/EvalCrafter"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/diverse-and-aligned-audio-to-video-generation","slug":"diverse-and-aligned-audio-to-video-generation","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","date":"2023-09-28","arxiv_id":"2309.16429","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/diverse-and-aligned-audio-to-video-generation#ran","syntology_url":"https://syntology.ai/paper/2309.16429","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16429"}},"official":{"repos":["guyyariv/TempoTokens"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/show-1-marrying-pixel-and-latent-diffusion","slug":"show-1-marrying-pixel-and-latent-diffusion","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","date":"2023-09-27","arxiv_id":"2309.15818","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/show-1-marrying-pixel-and-latent-diffusion#ran","syntology_url":"https://syntology.ai/paper/2309.15818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15818"}},"official":{"repos":["showlab/show-1"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lavie-high-quality-video-generation-with","slug":"lavie-high-quality-video-generation-with","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","date":"2023-09-26","arxiv_id":"2309.15103","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lavie-high-quality-video-generation-with#ran","syntology_url":"https://syntology.ai/paper/2309.15103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15103"}},"official":{"repos":["Vchitect/LaVie"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/free-bloom-zero-shot-text-to-video-generator","slug":"free-bloom-zero-shot-text-to-video-generator","title":"Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator","date":"2023-09-25","arxiv_id":"2309.14494","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/free-bloom-zero-shot-text-to-video-generator#ran","syntology_url":"https://syntology.ai/paper/2309.14494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.14494"}},"official":{"repos":["soolab/free-bloom"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/modelscope-text-to-video-technical-report","slug":"modelscope-text-to-video-technical-report","title":"ModelScope Text-to-Video Technical Report","date":"2023-08-12","arxiv_id":"2308.06571","repositories_listed":5,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/modelscope-text-to-video-technical-report#ran","syntology_url":"https://syntology.ai/paper/2308.06571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06571"}},"official":{"repos":["exponentialml/text-to-video-finetuning"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/videocomposer-compositional-video-synthesis","slug":"videocomposer-compositional-video-synthesis","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","date":"2023-06-03","arxiv_id":"2306.02018","repositories_listed":4,"syntology":{"n":21,"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/videocomposer-compositional-video-synthesis#ran","syntology_url":"https://syntology.ai/paper/2306.02018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02018"}},"official":null}},{"url":"/paper/large-language-models-are-frame-level","slug":"large-language-models-are-frame-level","title":"DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation","date":"2023-05-23","arxiv_id":"2305.14330","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-are-frame-level#ran","syntology_url":"https://syntology.ai/paper/2305.14330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14330"}},"official":{"repos":["ku-cvlab/direct2v"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/controlvideo-training-free-controllable-text","slug":"controlvideo-training-free-controllable-text","title":"ControlVideo: Training-free Controllable Text-to-Video Generation","date":"2023-05-22","arxiv_id":"2305.13077","repositories_listed":1,"syntology":{"n":9,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/controlvideo-training-free-controllable-text#ran","syntology_url":"https://syntology.ai/paper/2305.13077","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13077"}},"official":{"repos":["ybybzhang/controlvideo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/align-your-latents-high-resolution-video","slug":"align-your-latents-high-resolution-video","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","date":"2023-04-18","arxiv_id":"2304.08818","repositories_listed":4,"syntology":{"n":26,"n_ran":18,"n_constructed":0,"n_ran_checked":12,"n_instrument":6,"n_unverified":8,"n_honours":2,"n_violates":3,"n_no_contract":7,"n_pointer_only":3,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 3 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/align-your-latents-high-resolution-video#ran","syntology_url":"https://syntology.ai/paper/2304.08818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08818"}},"official":{"repos":["stability-ai/generative-models"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","listed","unlocated"]}}},{"url":"/paper/follow-your-pose-pose-guided-text-to-video","slug":"follow-your-pose-pose-guided-text-to-video","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","date":"2023-04-03","arxiv_id":"2304.01186","repositories_listed":2,"syntology":{"n":10,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/follow-your-pose-pose-guided-text-to-video#ran","syntology_url":"https://syntology.ai/paper/2304.01186","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.01186"}},"official":{"repos":["mayuelala/followyourpose"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/make-an-audio-text-to-audio-generation-with","slug":"make-an-audio-text-to-audio-generation-with","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","date":"2023-01-30","arxiv_id":"2301.12661","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/make-an-audio-text-to-audio-generation-with#ran","syntology_url":"https://syntology.ai/paper/2301.12661","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12661"}},"official":null}},{"url":"/paper/tune-a-video-one-shot-tuning-of-image","slug":"tune-a-video-one-shot-tuning-of-image","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","date":"2022-12-22","arxiv_id":"2212.11565","repositories_listed":3,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tune-a-video-one-shot-tuning-of-image#ran","syntology_url":"https://syntology.ai/paper/2212.11565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.11565"}},"official":{"repos":["showlab/Tune-A-Video"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/magvit-masked-generative-video-transformer","slug":"magvit-masked-generative-video-transformer","title":"MAGVIT: Masked Generative Video Transformer","date":"2022-12-10","arxiv_id":"2212.05199","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/magvit-masked-generative-video-transformer#ran","syntology_url":"https://syntology.ai/paper/2212.05199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.05199"}},"official":{"repos":["google-research/magvit"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/latent-video-diffusion-models-for-high","slug":"latent-video-diffusion-models-for-high","title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","date":"2022-11-23","arxiv_id":"2211.13221","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":5,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/latent-video-diffusion-models-for-high#ran","syntology_url":"https://syntology.ai/paper/2211.13221","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.13221"}},"official":{"repos":["yingqinghe/lvdm"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/nuwa-visual-synthesis-pre-training-for-neural","slug":"nuwa-visual-synthesis-pre-training-for-neural","title":"NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion","date":"2021-11-24","arxiv_id":"2111.12417","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/nuwa-visual-synthesis-pre-training-for-neural#ran","syntology_url":"https://syntology.ai/paper/2111.12417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12417"}},"official":null}}],"record_sha256":"87f354e1cc78f951e0e2b58bd4573bf2da08b141db5f0f17b75f46e9786eedaa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}