{"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/stablevideo-text-driven-consistency-aware","title":"StableVideo: Text-driven Consistency-aware Diffusion Video Editing","arxiv_id":"2308.09592","date":"2023-08-18","proceeding":"ICCV 2023 1","authors":["Wenhao Chai","Xun Guo","Gaoang Wang","Yan Lu"],"abstract":"Diffusion-based methods can generate realistic images and videos, but they struggle to edit existing objects in a video while preserving their appearance over time. This prevents diffusion models from being applied to natural video editing in practical scenarios. In this paper, we tackle this problem by introducing temporal dependency to existing text-driven diffusion models, which allows them to generate consistent appearance for the edited objects. Specifically, we develop a novel inter-frame propagation mechanism for diffusion video editing, which leverages the concept of layered representations to propagate the appearance information from one frame to the next. We then build up a text-driven video editing framework based on this mechanism, namely StableVideo, which can achieve consistency-aware video editing. Extensive experiments demonstrate the strong editing capability of our approach. Compared with state-of-the-art video editing methods, our approach shows superior qualitative and quantitative results. Our code is available at \\href{https://github.com/rese1f/StableVideo}{this https URL}.","url_abs":"https://arxiv.org/abs/2308.09592v1","url_pdf":"https://arxiv.org/pdf/2308.09592v1.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":"stablevideo-text-driven-consistency-aware","repo_url":"https://github.com/rese1f/stablevideo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"video-editing","task_name":"Video Editing"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.09592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09592"}},"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/rese1f/stablevideo","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"ran_honours":1,"ran_violates":2,"ran":2,"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":11,"ran":8,"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":"f9ec7d70add02b6f","entry":"HWC3","repo":"rese1f/stablevideo","repo_kind":"official","path":"annotator/util.py","file_url":"https://github.com/rese1f/stablevideo/blob/HEAD/annotator/util.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f9ec7d70add02b6f"}},{"code_sha256_prefix":"f6b944f50d3f15ae","entry":"count_parameters","repo":"rese1f/stablevideo","repo_kind":"official","path":"stablevideo/implicit_neural_networks.py","file_url":"https://github.com/rese1f/stablevideo/blob/HEAD/stablevideo/implicit_neural_networks.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f6b944f50d3f15ae"}},{"code_sha256_prefix":"424012cb37b31172","entry":"default","repo":"rese1f/stablevideo","repo_kind":"official","path":"ldm/modules/attention.py","file_url":"https://github.com/rese1f/stablevideo/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"424012cb37b31172"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"rese1f/stablevideo","repo_kind":"official","path":"ldm/modules/attention.py","file_url":"https://github.com/rese1f/stablevideo/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"265068c7d6082746","entry":"get_frames_data","repo":"rese1f/stablevideo","repo_kind":"official","path":"stablevideo/atlas_utils.py","file_url":"https://github.com/rese1f/stablevideo/blob/HEAD/stablevideo/atlas_utils.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":"265068c7d6082746"}},{"code_sha256_prefix":"b73c0affb20bb803","entry":"load_video","repo":"rese1f/stablevideo","repo_kind":"official","path":"stablevideo/atlas_utils.py","file_url":"https://github.com/rese1f/stablevideo/blob/HEAD/stablevideo/atlas_utils.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":"b73c0affb20bb803"}},{"code_sha256_prefix":"ab6aff4b59ac84d5","entry":"positionalEncoding_vec","repo":"rese1f/stablevideo","repo_kind":"official","path":"stablevideo/implicit_neural_networks.py","file_url":"https://github.com/rese1f/stablevideo/blob/HEAD/stablevideo/implicit_neural_networks.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ab6aff4b59ac84d5"}},{"code_sha256_prefix":"9a299fe5ae09e407","entry":"uniq","repo":"rese1f/stablevideo","repo_kind":"official","path":"ldm/modules/attention.py","file_url":"https://github.com/rese1f/stablevideo/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9a299fe5ae09e407"}},{"code_sha256_prefix":"cfc17707f35e7ec4","entry":"get_state_dict","repo":"rese1f/stablevideo","repo_kind":"official","path":"cldm/model.py","file_url":"https://github.com/rese1f/stablevideo/blob/HEAD/cldm/model.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":"cfc17707f35e7ec4"}},{"code_sha256_prefix":"df733a879693145d","entry":"load_state_dict","repo":"rese1f/stablevideo","repo_kind":"official","path":"cldm/model.py","file_url":"https://github.com/rese1f/stablevideo/blob/HEAD/cldm/model.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":"df733a879693145d"}},{"code_sha256_prefix":"50fd68f6989503c6","entry":"resize_image","repo":"rese1f/stablevideo","repo_kind":"official","path":"annotator/util.py","file_url":"https://github.com/rese1f/stablevideo/blob/HEAD/annotator/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":"50fd68f6989503c6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}