{"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/t2v-turbo-v2-enhancing-video-generation-model","title":"T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design","arxiv_id":"2410.05677","date":"2024-10-08","proceeding":null,"authors":["Jiachen Li","Qian Long","Jian Zheng","Xiaofeng Gao","Robinson Piramuthu","Wenhu Chen","William Yang Wang"],"abstract":"In this paper, we focus on enhancing a diffusion-based text-to-video (T2V) model during the post-training phase by distilling a highly capable consistency model from a pretrained T2V model. Our proposed method, T2V-Turbo-v2, introduces a significant advancement by integrating various supervision signals, including high-quality training data, reward model feedback, and conditional guidance, into the consistency distillation process. Through comprehensive ablation studies, we highlight the crucial importance of tailoring datasets to specific learning objectives and the effectiveness of learning from diverse reward models for enhancing both the visual quality and text-video alignment. Additionally, we highlight the vast design space of conditional guidance strategies, which centers on designing an effective energy function to augment the teacher ODE solver. We demonstrate the potential of this approach by extracting motion guidance from the training datasets and incorporating it into the ODE solver, showcasing its effectiveness in improving the motion quality of the generated videos with the improved motion-related metrics from VBench and T2V-CompBench. Empirically, our T2V-Turbo-v2 establishes a new state-of-the-art result on VBench, with a Total score of 85.13, surpassing proprietary systems such as Gen-3 and Kling.","url_abs":"https://arxiv.org/abs/2410.05677v2","url_pdf":"https://arxiv.org/pdf/2410.05677v2.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":"t2v-turbo-v2-enhancing-video-generation-model","repo_url":"https://github.com/Ji4chenLi/t2v-turbo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"video-alignment","task_name":"Video Alignment"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.05677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05677"}},"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/Ji4chenLi/t2v-turbo","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran":5,"ran_draft_wrong":2},"by_repo_kind":{"listed":{"samples":8,"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":8,"samples":[{"code_sha256_prefix":"8ca268a48aa60cb1","entry":"betas_for_alpha_bar","repo":"Ji4chenLi/t2v-turbo","repo_kind":"listed","path":"scheduler/t2v_turbo_scheduler.py","file_url":"https://github.com/Ji4chenLi/t2v-turbo/blob/HEAD/scheduler/t2v_turbo_scheduler.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8ca268a48aa60cb1"}},{"code_sha256_prefix":"7f3df606111e13f3","entry":"encode_prompt","repo":"Ji4chenLi/t2v-turbo","repo_kind":"listed","path":"train_t2v_turbo_v1_lora.py","file_url":"https://github.com/Ji4chenLi/t2v-turbo/blob/HEAD/train_t2v_turbo_v1_lora.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7f3df606111e13f3"}},{"code_sha256_prefix":"a15cfd7932844ef9","entry":"extract_into_tensor","repo":"Ji4chenLi/t2v-turbo","repo_kind":"listed","path":"scheduler/t2v_turbo_scheduler.py","file_url":"https://github.com/Ji4chenLi/t2v-turbo/blob/HEAD/scheduler/t2v_turbo_scheduler.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a15cfd7932844ef9"}},{"code_sha256_prefix":"8e4e26817e55a19c","entry":"get_temp_attn_prob","repo":"Ji4chenLi/t2v-turbo","repo_kind":"listed","path":"motion_prior_sample.py","file_url":"https://github.com/Ji4chenLi/t2v-turbo/blob/HEAD/motion_prior_sample.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8e4e26817e55a19c"}},{"code_sha256_prefix":"c1232f9d1e7794e4","entry":"is_video","repo":"Ji4chenLi/t2v-turbo","repo_kind":"listed","path":"model_scope/unet_3d_blocks.py","file_url":"https://github.com/Ji4chenLi/t2v-turbo/blob/HEAD/model_scope/unet_3d_blocks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c1232f9d1e7794e4"}},{"code_sha256_prefix":"1c00f3d9c2aa103c","entry":"randomize_seed_fn","repo":"Ji4chenLi/t2v-turbo","repo_kind":"listed","path":"app_ms.py","file_url":"https://github.com/Ji4chenLi/t2v-turbo/blob/HEAD/app_ms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1c00f3d9c2aa103c"}},{"code_sha256_prefix":"825af7863abcbfe2","entry":"rescale_zero_terminal_snr","repo":"Ji4chenLi/t2v-turbo","repo_kind":"listed","path":"scheduler/t2v_turbo_scheduler.py","file_url":"https://github.com/Ji4chenLi/t2v-turbo/blob/HEAD/scheduler/t2v_turbo_scheduler.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"825af7863abcbfe2"}},{"code_sha256_prefix":"d2917b78f49755cf","entry":"reverse_ddim_loop","repo":"Ji4chenLi/t2v-turbo","repo_kind":"listed","path":"motion_prior_sample.py","file_url":"https://github.com/Ji4chenLi/t2v-turbo/blob/HEAD/motion_prior_sample.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d2917b78f49755cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}