{"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/consistent-video-to-video-transfer-using","title":"Consistent Video-to-Video Transfer Using Synthetic Dataset","arxiv_id":"2311.00213","date":"2023-11-01","proceeding":null,"authors":["Jiaxin Cheng","Tianjun Xiao","Tong He"],"abstract":"We introduce a novel and efficient approach for text-based video-to-video editing that eliminates the need for resource-intensive per-video-per-model finetuning. At the core of our approach is a synthetic paired video dataset tailored for video-to-video transfer tasks. Inspired by Instruct Pix2Pix's image transfer via editing instruction, we adapt this paradigm to the video domain. Extending the Prompt-to-Prompt to videos, we efficiently generate paired samples, each with an input video and its edited counterpart. Alongside this, we introduce the Long Video Sampling Correction during sampling, ensuring consistent long videos across batches. Our method surpasses current methods like Tune-A-Video, heralding substantial progress in text-based video-to-video editing and suggesting exciting avenues for further exploration and deployment.","url_abs":"https://arxiv.org/abs/2311.00213v3","url_pdf":"https://arxiv.org/pdf/2311.00213v3.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":"consistent-video-to-video-transfer-using","repo_url":"https://github.com/amazon-science/instruct-video-to-video","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT-0"}}],"tasks":[{"task_slug":"video-editing","task_name":"Video Editing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.00213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.00213"}},"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/amazon-science/instruct-video-to-video","reach":{"status":"ok","spdx":"MIT-0"}}],"summary":{"ran_violates":2,"ran":3,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":9,"ran":6,"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":"d1ef6b8cb9a28a53","entry":"default","repo":"amazon-science/instruct-video-to-video","repo_kind":"official","path":"modules/damo_text_to_video/unet_sd.py","file_url":"https://github.com/amazon-science/instruct-video-to-video/blob/HEAD/modules/damo_text_to_video/unet_sd.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT-0","inline_ok":true,"mcp_get_code":{"code_sha256":"d1ef6b8cb9a28a53"}},{"code_sha256_prefix":"608e364a9d2376a3","entry":"exists","repo":"amazon-science/instruct-video-to-video","repo_kind":"official","path":"modules/damo_text_to_video/unet_sd.py","file_url":"https://github.com/amazon-science/instruct-video-to-video/blob/HEAD/modules/damo_text_to_video/unet_sd.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT-0","inline_ok":true,"mcp_get_code":{"code_sha256":"608e364a9d2376a3"}},{"code_sha256_prefix":"beb7e713c34bf484","entry":"frame_dim_to_batch_dim","repo":"amazon-science/instruct-video-to-video","repo_kind":"official","path":"callbacks/instruct_p2p_video.py","file_url":"https://github.com/amazon-science/instruct-video-to-video/blob/HEAD/callbacks/instruct_p2p_video.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT-0","inline_ok":true,"mcp_get_code":{"code_sha256":"beb7e713c34bf484"}},{"code_sha256_prefix":"b2527fed746fee97","entry":"sinusoidal_embedding","repo":"amazon-science/instruct-video-to-video","repo_kind":"official","path":"modules/damo_text_to_video/unet_sd.py","file_url":"https://github.com/amazon-science/instruct-video-to-video/blob/HEAD/modules/damo_text_to_video/unet_sd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT-0","inline_ok":true,"mcp_get_code":{"code_sha256":"b2527fed746fee97"}},{"code_sha256_prefix":"dc99b4575f2bba57","entry":"torch_to_numpy","repo":"amazon-science/instruct-video-to-video","repo_kind":"official","path":"video_prompt_to_prompt.py","file_url":"https://github.com/amazon-science/instruct-video-to-video/blob/HEAD/video_prompt_to_prompt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT-0","inline_ok":true,"mcp_get_code":{"code_sha256":"dc99b4575f2bba57"}},{"code_sha256_prefix":"4719c763c53be3fe","entry":"zero_module","repo":"amazon-science/instruct-video-to-video","repo_kind":"official","path":"modules/video_unet_temporal/motion_module.py","file_url":"https://github.com/amazon-science/instruct-video-to-video/blob/HEAD/modules/video_unet_temporal/motion_module.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT-0","inline_ok":true,"mcp_get_code":{"code_sha256":"4719c763c53be3fe"}},{"code_sha256_prefix":"6b48cad564c06360","entry":"get_down_block","repo":"amazon-science/instruct-video-to-video","repo_kind":"official","path":"modules/video_unet_temporal/unet_blocks.py","file_url":"https://github.com/amazon-science/instruct-video-to-video/blob/HEAD/modules/video_unet_temporal/unet_blocks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT-0","inline_ok":true,"mcp_get_code":{"code_sha256":"6b48cad564c06360"}},{"code_sha256_prefix":"878e2de1767b92d2","entry":"get_motion_module","repo":"amazon-science/instruct-video-to-video","repo_kind":"official","path":"modules/video_unet_temporal/motion_module.py","file_url":"https://github.com/amazon-science/instruct-video-to-video/blob/HEAD/modules/video_unet_temporal/motion_module.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT-0","inline_ok":true,"mcp_get_code":{"code_sha256":"878e2de1767b92d2"}},{"code_sha256_prefix":"2609ced19ec5ef16","entry":"get_up_block","repo":"amazon-science/instruct-video-to-video","repo_kind":"official","path":"modules/video_unet_temporal/unet_blocks.py","file_url":"https://github.com/amazon-science/instruct-video-to-video/blob/HEAD/modules/video_unet_temporal/unet_blocks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT-0","inline_ok":true,"mcp_get_code":{"code_sha256":"2609ced19ec5ef16"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}