{"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/extrapolating-and-decoupling-image-to-video","title":"Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think","arxiv_id":"2503.00948","date":"2025-03-02","proceeding":"CVPR 2025 1","authors":["Jie Tian","Xiaoye Qu","Zhenyi Lu","Wei Wei","Sichen Liu","Yu Cheng"],"abstract":"Image-to-Video (I2V) generation aims to synthesize a video clip according to a given image and condition (e.g., text). The key challenge of this task lies in simultaneously generating natural motions while preserving the original appearance of the images. However, current I2V diffusion models (I2V-DMs) often produce videos with limited motion degrees or exhibit uncontrollable motion that conflicts with the textual condition. To address these limitations, we propose a novel Extrapolating and Decoupling framework, which introduces model merging techniques to the I2V domain for the first time. Specifically, our framework consists of three separate stages: (1) Starting with a base I2V-DM, we explicitly inject the textual condition into the temporal module using a lightweight, learnable adapter and fine-tune the integrated model to improve motion controllability. (2) We introduce a training-free extrapolation strategy to amplify the dynamic range of the motion, effectively reversing the fine-tuning process to enhance the motion degree significantly. (3) With the above two-stage models excelling in motion controllability and degree, we decouple the relevant parameters associated with each type of motion ability and inject them into the base I2V-DM. Since the I2V-DM handles different levels of motion controllability and dynamics at various denoising time steps, we adjust the motion-aware parameters accordingly over time. Extensive qualitative and quantitative experiments have been conducted to demonstrate the superiority of our framework over existing methods.","url_abs":"https://arxiv.org/abs/2503.00948v1","url_pdf":"https://arxiv.org/pdf/2503.00948v1.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":"extrapolating-and-decoupling-image-to-video","repo_url":"https://github.com/Chuge0335/EDG","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-to-video","task_name":"Image to Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"base","method_name":"BASE"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.00948","atlas_url":"https://app.syntology.ai/?focus=2503.00948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.00948"}},"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":"deterministic:regex_extraction","url":"https://github.com/Chuge0335/EDG","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"ran_draft_wrong":4,"ran":6,"unverified":4},"by_repo_kind":{"official":{"samples":15,"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":"4cb732f513d69dfd","entry":"disabled_train","repo":"Chuge0335/EDG","repo_kind":"official","path":"lvdm/basics.py","file_url":"https://github.com/Chuge0335/EDG/blob/HEAD/lvdm/basics.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"a15cfd7932844ef9","entry":"extract_into_tensor","repo":"Chuge0335/EDG","repo_kind":"official","path":"lvdm/common.py","file_url":"https://github.com/Chuge0335/EDG/blob/HEAD/lvdm/common.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a15cfd7932844ef9"}},{"code_sha256_prefix":"0aa0f88278338151","entry":"get_dirlist","repo":"Chuge0335/EDG","repo_kind":"official","path":"evaluation/funcs.py","file_url":"https://github.com/Chuge0335/EDG/blob/HEAD/evaluation/funcs.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":"0aa0f88278338151"}},{"code_sha256_prefix":"47c2ca5ed028e21d","entry":"get_filelist","repo":"Chuge0335/EDG","repo_kind":"official","path":"evaluation/funcs.py","file_url":"https://github.com/Chuge0335/EDG/blob/HEAD/evaluation/funcs.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":"47c2ca5ed028e21d"}},{"code_sha256_prefix":"cd9fc7fd42461147","entry":"get_filelist","repo":"Chuge0335/EDG","repo_kind":"official","path":"evaluation/infer_multi.py","file_url":"https://github.com/Chuge0335/EDG/blob/HEAD/evaluation/infer_multi.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":"cd9fc7fd42461147"}},{"code_sha256_prefix":"221b2d116fdf1032","entry":"get_obj_from_str","repo":"Chuge0335/EDG","repo_kind":"official","path":"merge/model.py","file_url":"https://github.com/Chuge0335/EDG/blob/HEAD/merge/model.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","inline_ok":true,"mcp_get_code":{"code_sha256":"221b2d116fdf1032"}},{"code_sha256_prefix":"579247b6fbbc2cd7","entry":"load_model_checkpoint","repo":"Chuge0335/EDG","repo_kind":"official","path":"merge/model.py","file_url":"https://github.com/Chuge0335/EDG/blob/HEAD/merge/model.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":"579247b6fbbc2cd7"}},{"code_sha256_prefix":"a9d9177dbb51afed","entry":"load_model_checkpoint","repo":"Chuge0335/EDG","repo_kind":"official","path":"evaluation/infer_multi.py","file_url":"https://github.com/Chuge0335/EDG/blob/HEAD/evaluation/infer_multi.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":"a9d9177dbb51afed"}},{"code_sha256_prefix":"ea66ba28a2e932e1","entry":"load_prompts","repo":"Chuge0335/EDG","repo_kind":"official","path":"evaluation/infer_multi.py","file_url":"https://github.com/Chuge0335/EDG/blob/HEAD/evaluation/infer_multi.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","inline_ok":true,"mcp_get_code":{"code_sha256":"ea66ba28a2e932e1"}},{"code_sha256_prefix":"17eb0a31c91b671c","entry":"normal_kl","repo":"Chuge0335/EDG","repo_kind":"official","path":"lvdm/distributions.py","file_url":"https://github.com/Chuge0335/EDG/blob/HEAD/lvdm/distributions.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":"17eb0a31c91b671c"}},{"code_sha256_prefix":"129b804760b3115f","entry":"zero_module","repo":"Chuge0335/EDG","repo_kind":"official","path":"lvdm/basics.py","file_url":"https://github.com/Chuge0335/EDG/blob/HEAD/lvdm/basics.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","inline_ok":true,"mcp_get_code":{"code_sha256":"129b804760b3115f"}},{"code_sha256_prefix":"32af1c12fd826ef2","entry":"autocast","repo":"Chuge0335/EDG","repo_kind":"official","path":"lvdm/common.py","file_url":"https://github.com/Chuge0335/EDG/blob/HEAD/lvdm/common.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":"32af1c12fd826ef2"}},{"code_sha256_prefix":"b72d8eb89fd75383","entry":"gather_data","repo":"Chuge0335/EDG","repo_kind":"official","path":"lvdm/common.py","file_url":"https://github.com/Chuge0335/EDG/blob/HEAD/lvdm/common.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":"b72d8eb89fd75383"}},{"code_sha256_prefix":"ef52d142b2c30ac2","entry":"instantiate_from_config","repo":"Chuge0335/EDG","repo_kind":"official","path":"merge/model.py","file_url":"https://github.com/Chuge0335/EDG/blob/HEAD/merge/model.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":"ef52d142b2c30ac2"}},{"code_sha256_prefix":"9136b5f9b735334b","entry":"scale_module","repo":"Chuge0335/EDG","repo_kind":"official","path":"lvdm/basics.py","file_url":"https://github.com/Chuge0335/EDG/blob/HEAD/lvdm/basics.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":"9136b5f9b735334b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}