{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/modelscope-text-to-video-technical-report","title":"ModelScope Text-to-Video Technical Report","arxiv_id":"2308.06571","date":"2023-08-12","proceeding":null,"authors":["Jiuniu Wang","Hangjie Yuan","Dayou Chen","Yingya Zhang","Xiang Wang","Shiwei Zhang"],"abstract":"This paper introduces ModelScopeT2V, a text-to-video synthesis model that evolves from a text-to-image synthesis model (i.e., Stable Diffusion). ModelScopeT2V incorporates spatio-temporal blocks to ensure consistent frame generation and smooth movement transitions. The model could adapt to varying frame numbers during training and inference, rendering it suitable for both image-text and video-text datasets. ModelScopeT2V brings together three components (i.e., VQGAN, a text encoder, and a denoising UNet), totally comprising 1.7 billion parameters, in which 0.5 billion parameters are dedicated to temporal capabilities. The model demonstrates superior performance over state-of-the-art methods across three evaluation metrics. The code and an online demo are available at \\url{https://modelscope.cn/models/damo/text-to-video-synthesis/summary}.","url_abs":"https://arxiv.org/abs/2308.06571v1","url_pdf":"https://arxiv.org/pdf/2308.06571v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"modelscope-text-to-video-technical-report","repo_url":"https://github.com/exponentialml/text-to-video-finetuning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"modelscope-text-to-video-technical-report","repo_url":"https://github.com/ali-vilab/VGen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"modelscope-text-to-video-technical-report","repo_url":"https://github.com/ali-vilab/i2vgen-xl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"modelscope-text-to-video-technical-report","repo_url":"https://github.com/picsart-ai-research/streamingt2v","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"modelscope-text-to-video-technical-report","repo_url":"https://github.com/yhZhai/mcm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"text-to-video-generation","task_name":"Text-to-Video Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-video-generation-on-msr-vtt","task":"Text-to-Video Generation","dataset":"MSR-VTT","model":"ModelScopeT2V","rank_in_archive_order":9,"of":18,"metrics":{"CLIPSIM":"0.2930","FID":"11.09","FVD":"550"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2308.06571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06571"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/exponentialml/text-to-video-finetuning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yhZhai/mcm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ali-vilab/VGen","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ali-vilab/i2vgen-xl","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/picsart-ai-research/streamingt2v","reach":{"status":"ok"}}],"summary":{"ran":11,"unverified":5},"by_repo_kind":{"official":{"samples":16,"ran":11,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a59539766c1c5a5a","entry":"convert_text_enc_state_dict","repo":"exponentialml/text-to-video-finetuning","repo_kind":"official","path":"utils/convert_diffusers_to_original_ms_text_to_video.py","file_url":"https://github.com/exponentialml/text-to-video-finetuning/blob/HEAD/utils/convert_diffusers_to_original_ms_text_to_video.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a59539766c1c5a5a"}},{"code_sha256_prefix":"8d4b0c9f8b9a884e","entry":"convert_text_enc_state_dict_v20","repo":"exponentialml/text-to-video-finetuning","repo_kind":"official","path":"utils/convert_diffusers_to_original_ms_text_to_video.py","file_url":"https://github.com/exponentialml/text-to-video-finetuning/blob/HEAD/utils/convert_diffusers_to_original_ms_text_to_video.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d4b0c9f8b9a884e"}},{"code_sha256_prefix":"bfdb56f5b6ab8034","entry":"download_progress","repo":"exponentialml/text-to-video-finetuning","repo_kind":"official","path":"utils/lama.py","file_url":"https://github.com/exponentialml/text-to-video-finetuning/blob/HEAD/utils/lama.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bfdb56f5b6ab8034"}},{"code_sha256_prefix":"9191602362628ded","entry":"filter_dict","repo":"exponentialml/text-to-video-finetuning","repo_kind":"official","path":"utils/lora_handler.py","file_url":"https://github.com/exponentialml/text-to-video-finetuning/blob/HEAD/utils/lora_handler.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9191602362628ded"}},{"code_sha256_prefix":"8ff113de21fb6bc2","entry":"get_bucket_sizes","repo":"exponentialml/text-to-video-finetuning","repo_kind":"official","path":"utils/bucketing.py","file_url":"https://github.com/exponentialml/text-to-video-finetuning/blob/HEAD/utils/bucketing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ff113de21fb6bc2"}},{"code_sha256_prefix":"6f7c993202e44dda","entry":"get_prompt_ids","repo":"exponentialml/text-to-video-finetuning","repo_kind":"official","path":"utils/dataset.py","file_url":"https://github.com/exponentialml/text-to-video-finetuning/blob/HEAD/utils/dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f7c993202e44dda"}},{"code_sha256_prefix":"c1232f9d1e7794e4","entry":"is_video","repo":"exponentialml/text-to-video-finetuning","repo_kind":"official","path":"models/unet_3d_blocks.py","file_url":"https://github.com/exponentialml/text-to-video-finetuning/blob/HEAD/models/unet_3d_blocks.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c1232f9d1e7794e4"}},{"code_sha256_prefix":"40775842d99a25f9","entry":"min_res","repo":"exponentialml/text-to-video-finetuning","repo_kind":"official","path":"utils/bucketing.py","file_url":"https://github.com/exponentialml/text-to-video-finetuning/blob/HEAD/utils/bucketing.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"40775842d99a25f9"}},{"code_sha256_prefix":"dbfc36f5a5a5a1fd","entry":"normalize_input","repo":"exponentialml/text-to-video-finetuning","repo_kind":"official","path":"utils/dataset.py","file_url":"https://github.com/exponentialml/text-to-video-finetuning/blob/HEAD/utils/dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dbfc36f5a5a5a1fd"}},{"code_sha256_prefix":"00090fcbdd45d352","entry":"read_caption_file","repo":"exponentialml/text-to-video-finetuning","repo_kind":"official","path":"utils/dataset.py","file_url":"https://github.com/exponentialml/text-to-video-finetuning/blob/HEAD/utils/dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00090fcbdd45d352"}},{"code_sha256_prefix":"bec7ef14686681c0","entry":"up_down_bucket","repo":"exponentialml/text-to-video-finetuning","repo_kind":"official","path":"utils/bucketing.py","file_url":"https://github.com/exponentialml/text-to-video-finetuning/blob/HEAD/utils/bucketing.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bec7ef14686681c0"}},{"code_sha256_prefix":"754cea3454b8b8da","entry":"convert_unet_state_dict","repo":"exponentialml/text-to-video-finetuning","repo_kind":"official","path":"utils/convert_diffusers_to_original_ms_text_to_video.py","file_url":"https://github.com/exponentialml/text-to-video-finetuning/blob/HEAD/utils/convert_diffusers_to_original_ms_text_to_video.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"754cea3454b8b8da"}},{"code_sha256_prefix":"df1f737e7e9ec97f","entry":"inject_inferable_lora","repo":"exponentialml/text-to-video-finetuning","repo_kind":"official","path":"utils/lora.py","file_url":"https://github.com/exponentialml/text-to-video-finetuning/blob/HEAD/utils/lora.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df1f737e7e9ec97f"}},{"code_sha256_prefix":"da50048edb81475c","entry":"inject_trainable_lora","repo":"exponentialml/text-to-video-finetuning","repo_kind":"official","path":"utils/lora.py","file_url":"https://github.com/exponentialml/text-to-video-finetuning/blob/HEAD/utils/lora.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da50048edb81475c"}},{"code_sha256_prefix":"929d4d45fed75939","entry":"inject_trainable_lora_extended","repo":"exponentialml/text-to-video-finetuning","repo_kind":"official","path":"utils/lora.py","file_url":"https://github.com/exponentialml/text-to-video-finetuning/blob/HEAD/utils/lora.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"929d4d45fed75939"}},{"code_sha256_prefix":"3c2dce662245aae1","entry":"inpaint_watermark","repo":"exponentialml/text-to-video-finetuning","repo_kind":"official","path":"utils/lama.py","file_url":"https://github.com/exponentialml/text-to-video-finetuning/blob/HEAD/utils/lama.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c2dce662245aae1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}