{"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/tune-a-video-one-shot-tuning-of-image","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","arxiv_id":"2212.11565","date":"2022-12-22","proceeding":"ICCV 2023 1","authors":["Jay Zhangjie Wu","Yixiao Ge","Xintao Wang","Weixian Lei","YuChao Gu","Yufei Shi","Wynne Hsu","Ying Shan","XiaoHu Qie","Mike Zheng Shou"],"abstract":"To replicate the success of text-to-image (T2I) generation, recent works employ large-scale video datasets to train a text-to-video (T2V) generator. Despite their promising results, such paradigm is computationally expensive. In this work, we propose a new T2V generation setting$\\unicode{x2014}$One-Shot Video Tuning, where only one text-video pair is presented. Our model is built on state-of-the-art T2I diffusion models pre-trained on massive image data. We make two key observations: 1) T2I models can generate still images that represent verb terms; 2) extending T2I models to generate multiple images concurrently exhibits surprisingly good content consistency. To further learn continuous motion, we introduce Tune-A-Video, which involves a tailored spatio-temporal attention mechanism and an efficient one-shot tuning strategy. At inference, we employ DDIM inversion to provide structure guidance for sampling. Extensive qualitative and numerical experiments demonstrate the remarkable ability of our method across various applications.","url_abs":"https://arxiv.org/abs/2212.11565v2","url_pdf":"https://arxiv.org/pdf/2212.11565v2.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":"tune-a-video-one-shot-tuning-of-image","repo_url":"https://github.com/showlab/Tune-A-Video","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"tune-a-video-one-shot-tuning-of-image","repo_url":"https://github.com/showlab/loveu-tgve-2023","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tune-a-video-one-shot-tuning-of-image","repo_url":"https://github.com/xuduo35/MakeLongVideo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"style-transfer","task_name":"Style Transfer"},{"task_slug":"text-to-video-generation","task_name":"Text-to-Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.11565","atlas_url":"https://app.syntology.ai/?focus=2212.11565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.11565"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/showlab/loveu-tgve-2023","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xuduo35/MakeLongVideo","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/showlab/Tune-A-Video","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"repositories":1},"listed":{"samples":1,"ran":1,"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":"0b088617d5525751","entry":"get_noise_pred_single","repo":"showlab/Tune-A-Video","repo_kind":"official","path":"tuneavideo/util.py","file_url":"https://github.com/showlab/Tune-A-Video/blob/HEAD/tuneavideo/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0b088617d5525751"}},{"code_sha256_prefix":"fb032d6fa7e6196d","entry":"next_step","repo":"showlab/Tune-A-Video","repo_kind":"official","path":"tuneavideo/util.py","file_url":"https://github.com/showlab/Tune-A-Video/blob/HEAD/tuneavideo/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fb032d6fa7e6196d"}},{"code_sha256_prefix":"95f1f1a03d331768","entry":"randstr","repo":"xuduo35/MakeLongVideo","repo_kind":"listed","path":"infer.py","file_url":"https://github.com/xuduo35/MakeLongVideo/blob/HEAD/infer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"95f1f1a03d331768"}},{"code_sha256_prefix":"a362e5b7a1be4609","entry":"get_down_block","repo":"showlab/Tune-A-Video","repo_kind":"official","path":"tuneavideo/models/unet_blocks.py","file_url":"https://github.com/showlab/Tune-A-Video/blob/HEAD/tuneavideo/models/unet_blocks.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a362e5b7a1be4609"}},{"code_sha256_prefix":"01feceecb56a7ffb","entry":"get_up_block","repo":"showlab/Tune-A-Video","repo_kind":"official","path":"tuneavideo/models/unet_blocks.py","file_url":"https://github.com/showlab/Tune-A-Video/blob/HEAD/tuneavideo/models/unet_blocks.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"01feceecb56a7ffb"}},{"code_sha256_prefix":"a0a4d94af120c56f","entry":"init_prompt","repo":"showlab/Tune-A-Video","repo_kind":"official","path":"tuneavideo/util.py","file_url":"https://github.com/showlab/Tune-A-Video/blob/HEAD/tuneavideo/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a0a4d94af120c56f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}