{"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/vace-all-in-one-video-creation-and-editing","title":"VACE: All-in-One Video Creation and Editing","arxiv_id":"2503.07598","date":"2025-03-10","proceeding":null,"authors":["Zeyinzi Jiang","Zhen Han","Chaojie Mao","Jingfeng Zhang","Yulin Pan","Yu Liu"],"abstract":"Diffusion Transformer has demonstrated powerful capability and scalability in generating high-quality images and videos. Further pursuing the unification of generation and editing tasks has yielded significant progress in the domain of image content creation. However, due to the intrinsic demands for consistency across both temporal and spatial dynamics, achieving a unified approach for video synthesis remains challenging. We introduce VACE, which enables users to perform Video tasks within an All-in-one framework for Creation and Editing. These tasks include reference-to-video generation, video-to-video editing, and masked video-to-video editing. Specifically, we effectively integrate the requirements of various tasks by organizing video task inputs, such as editing, reference, and masking, into a unified interface referred to as the Video Condition Unit (VCU). Furthermore, by utilizing a Context Adapter structure, we inject different task concepts into the model using formalized representations of temporal and spatial dimensions, allowing it to handle arbitrary video synthesis tasks flexibly. Extensive experiments demonstrate that the unified model of VACE achieves performance on par with task-specific models across various subtasks. Simultaneously, it enables diverse applications through versatile task combinations. Project page: https://ali-vilab.github.io/VACE-Page/.","url_abs":"https://arxiv.org/abs/2503.07598v1","url_pdf":"https://arxiv.org/pdf/2503.07598v1.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":"vace-all-in-one-video-creation-and-editing","repo_url":"https://github.com/ali-vilab/vace","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"vace-all-in-one-video-creation-and-editing","repo_url":"https://github.com/wan-video/wan2.1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"human-domain-subject-to-video","task_name":"Human-Domain Subject-to-Video"},{"task_slug":"open-domain-subject-to-video","task_name":"Open-Domain Subject-to-Video"},{"task_slug":"single-domain-subject-to-video","task_name":"Single-Domain Subject-to-Video"},{"task_slug":"video-editing","task_name":"Video Editing"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-domain-subject-to-video-on-opens2v-eval","task":"Open-Domain Subject-to-Video","dataset":"OpenS2V-Eval","model":"Wan2.1-VACE-14B","rank_in_archive_order":2,"of":10,"metrics":{"Aesthetics":"0.4721","FaceSim":"0.5509","GmeScore":"0.6727","Motion":"0.1502","NaturalScore":"0.7278","NexusScore":"0.4420","Total Score":"0.5287","Venue":"Open-Source"},"uses_additional_data":false},{"leaderboard":"/sota/open-domain-subject-to-video-on-opens2v-eval","task":"Open-Domain Subject-to-Video","dataset":"OpenS2V-Eval","model":"Wan2.1-VACE-1.3B","rank_in_archive_order":9,"of":10,"metrics":{"Aesthetics":"0.4824","FaceSim":"0.2058","GmeScore":"0.7126","Motion":"0.1883","NaturalScore":"0.7178","NexusScore":"0.3795","Total Score":"0.4553","Venue":"Open-Source"},"uses_additional_data":false},{"leaderboard":"/sota/open-domain-subject-to-video-on-opens2v-eval","task":"Open-Domain Subject-to-Video","dataset":"OpenS2V-Eval","model":"Wan2.1-VACE-1.3B-Preview","rank_in_archive_order":10,"of":10,"metrics":{"Aesthetics":"0.4727","FaceSim":"0.1658","GmeScore":"0.7138","Motion":"0.1203","NaturalScore":"0.7056","NexusScore":"0.4004","Total Score":"0.4395","Venue":"Open-Source"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2503.07598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07598"}},"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/ali-vilab/vace","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wan-video/wan2.1","reach":null}],"summary":{"ran":5,"ran_draft_wrong":1,"ran_violates":1,"ran_fixture":1,"unverified":11},"by_repo_kind":{"listed":{"samples":19,"ran":8,"repositories":2}},"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":"9227be90bae9b073","entry":"Head","repo":"wan-video/wan2.1","repo_kind":"listed","path":"wan/modules/vace_model.py","file_url":"https://github.com/wan-video/wan2.1/blob/HEAD/wan/modules/vace_model.py","link_basis":"first_harvest_node","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":"9227be90bae9b073"}},{"code_sha256_prefix":"a30839494a20b1e1","entry":"MLPProj","repo":"wan-video/wan2.1","repo_kind":"listed","path":"wan/modules/vace_model.py","file_url":"https://github.com/wan-video/wan2.1/blob/HEAD/wan/modules/vace_model.py","link_basis":"first_harvest_node","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":"a30839494a20b1e1"}},{"code_sha256_prefix":"414694f69ae6b8f9","entry":"WanLayerNorm","repo":"wan-video/wan2.1","repo_kind":"listed","path":"wan/modules/vace_model.py","file_url":"https://github.com/wan-video/wan2.1/blob/HEAD/wan/modules/vace_model.py","link_basis":"first_harvest_node","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":"414694f69ae6b8f9"}},{"code_sha256_prefix":"f0af233187c10512","entry":"WanRMSNorm","repo":"wan-video/wan2.1","repo_kind":"listed","path":"wan/modules/vace_model.py","file_url":"https://github.com/wan-video/wan2.1/blob/HEAD/wan/modules/vace_model.py","link_basis":"first_harvest_node","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":"f0af233187c10512"}},{"code_sha256_prefix":"f929177cb0050047","entry":"WanSelfAttention","repo":"wan-video/wan2.1","repo_kind":"listed","path":"wan/modules/vace_model.py","file_url":"https://github.com/wan-video/wan2.1/blob/HEAD/wan/modules/vace_model.py","link_basis":"first_harvest_node","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":"f929177cb0050047"}},{"code_sha256_prefix":"1d28c4a06c930d63","entry":"rope_apply","repo":"wan-video/wan2.1","repo_kind":"listed","path":"wan/modules/vace_model.py","file_url":"https://github.com/wan-video/wan2.1/blob/HEAD/wan/modules/vace_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1d28c4a06c930d63"}},{"code_sha256_prefix":"dc160d63c5846f4a","entry":"rope_params","repo":"wan-video/wan2.1","repo_kind":"listed","path":"wan/modules/vace_model.py","file_url":"https://github.com/wan-video/wan2.1/blob/HEAD/wan/modules/vace_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dc160d63c5846f4a"}},{"code_sha256_prefix":"e34a97853e924d88","entry":"sinusoidal_embedding_1d","repo":"wan-video/wan2.1","repo_kind":"listed","path":"wan/modules/vace_model.py","file_url":"https://github.com/wan-video/wan2.1/blob/HEAD/wan/modules/vace_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e34a97853e924d88"}},{"code_sha256_prefix":"d8fbfa2bfc03756b","entry":"BaseWanAttentionBlock","repo":"wan-video/wan2.1","repo_kind":"listed","path":"wan/modules/vace_model.py","file_url":"https://github.com/wan-video/wan2.1/blob/HEAD/wan/modules/vace_model.py","link_basis":"first_harvest_node","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":"d8fbfa2bfc03756b"}},{"code_sha256_prefix":"3bfd0f1f0b483509","entry":"VaceWanAttentionBlock","repo":"wan-video/wan2.1","repo_kind":"listed","path":"wan/modules/vace_model.py","file_url":"https://github.com/wan-video/wan2.1/blob/HEAD/wan/modules/vace_model.py","link_basis":"first_harvest_node","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":"3bfd0f1f0b483509"}},{"code_sha256_prefix":"f640e494f36aac4d","entry":"VaceWanModel","repo":"wan-video/wan2.1","repo_kind":"listed","path":"wan/modules/vace_model.py","file_url":"https://github.com/wan-video/wan2.1/blob/HEAD/wan/modules/vace_model.py","link_basis":"first_harvest_node","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":"f640e494f36aac4d"}},{"code_sha256_prefix":"1e5313e0a5236094","entry":"WanAttentionBlock","repo":"wan-video/wan2.1","repo_kind":"listed","path":"wan/modules/vace_model.py","file_url":"https://github.com/wan-video/wan2.1/blob/HEAD/wan/modules/vace_model.py","link_basis":"first_harvest_node","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":"1e5313e0a5236094"}},{"code_sha256_prefix":"9a0c2329e53e9f65","entry":"WanI2VCrossAttention","repo":"wan-video/wan2.1","repo_kind":"listed","path":"wan/modules/vace_model.py","file_url":"https://github.com/wan-video/wan2.1/blob/HEAD/wan/modules/vace_model.py","link_basis":"first_harvest_node","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":"9a0c2329e53e9f65"}},{"code_sha256_prefix":"cf6067d2fe5bbb8c","entry":"WanModel","repo":"wan-video/wan2.1","repo_kind":"listed","path":"wan/modules/vace_model.py","file_url":"https://github.com/wan-video/wan2.1/blob/HEAD/wan/modules/vace_model.py","link_basis":"first_harvest_node","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":"cf6067d2fe5bbb8c"}},{"code_sha256_prefix":"1bae0faad8dabcc7","entry":"WanT2VCrossAttention","repo":"wan-video/wan2.1","repo_kind":"listed","path":"wan/modules/vace_model.py","file_url":"https://github.com/wan-video/wan2.1/blob/HEAD/wan/modules/vace_model.py","link_basis":"first_harvest_node","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":"1bae0faad8dabcc7"}},{"code_sha256_prefix":"76567eccecdf7882","entry":"filter_args","repo":"ali-vilab/vace","repo_kind":"listed","path":"vace/vace_pipeline.py","file_url":"https://github.com/ali-vilab/vace/blob/HEAD/vace/vace_pipeline.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":"76567eccecdf7882"}},{"code_sha256_prefix":"7ea44a4680b76539","entry":"flash_attention","repo":"wan-video/wan2.1","repo_kind":"listed","path":"wan/modules/vace_model.py","file_url":"https://github.com/wan-video/wan2.1/blob/HEAD/wan/modules/vace_model.py","link_basis":"first_harvest_node","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":"7ea44a4680b76539"}},{"code_sha256_prefix":"eb2897a72245d867","entry":"load_parser","repo":"ali-vilab/vace","repo_kind":"listed","path":"vace/vace_pipeline.py","file_url":"https://github.com/ali-vilab/vace/blob/HEAD/vace/vace_pipeline.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":"eb2897a72245d867"}},{"code_sha256_prefix":"73fe09ee58b99eef","entry":"parse_bboxes","repo":"ali-vilab/vace","repo_kind":"listed","path":"vace/vace_preproccess.py","file_url":"https://github.com/ali-vilab/vace/blob/HEAD/vace/vace_preproccess.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":"73fe09ee58b99eef"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}