{"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/vchitect-2-0-parallel-transformer-for-scaling","title":"Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models","arxiv_id":"2501.08453","date":"2025-01-14","proceeding":null,"authors":["Weichen Fan","Chenyang Si","Junhao Song","Zhenyu Yang","Yinan He","Long Zhuo","Ziqi Huang","Ziyue Dong","Jingwen He","Dongwei Pan","Yi Wang","Yuming Jiang","Yaohui Wang","Peng Gao","Xinyuan Chen","Hengjie Li","Dahua Lin","Yu Qiao","Ziwei Liu"],"abstract":"We present Vchitect-2.0, a parallel transformer architecture designed to scale up video diffusion models for large-scale text-to-video generation. The overall Vchitect-2.0 system has several key designs. (1) By introducing a novel Multimodal Diffusion Block, our approach achieves consistent alignment between text descriptions and generated video frames, while maintaining temporal coherence across sequences. (2) To overcome memory and computational bottlenecks, we propose a Memory-efficient Training framework that incorporates hybrid parallelism and other memory reduction techniques, enabling efficient training of long video sequences on distributed systems. (3) Additionally, our enhanced data processing pipeline ensures the creation of Vchitect T2V DataVerse, a high-quality million-scale training dataset through rigorous annotation and aesthetic evaluation. Extensive benchmarking demonstrates that Vchitect-2.0 outperforms existing methods in video quality, training efficiency, and scalability, serving as a suitable base for high-fidelity video generation.","url_abs":"https://arxiv.org/abs/2501.08453v1","url_pdf":"https://arxiv.org/pdf/2501.08453v1.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":"vchitect-2-0-parallel-transformer-for-scaling","repo_url":"https://github.com/Vchitect/Vchitect-2.0","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"text-to-video-generation","task_name":"Text-to-Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2501.08453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.08453"}},"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/Vchitect/Vchitect-2.0","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"listed":{"samples":7,"ran":1,"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":"0b56680ee1708fee","entry":"retrieve_timesteps","repo":"Vchitect/Vchitect-2.0","repo_kind":"listed","path":"models/pipeline.py","file_url":"https://github.com/Vchitect/Vchitect-2.0/blob/HEAD/models/pipeline.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0b56680ee1708fee"}},{"code_sha256_prefix":"43bd88e3a641a3b8","entry":"images_to_gif_bytes","repo":"Vchitect/Vchitect-2.0","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/Vchitect/Vchitect-2.0/blob/HEAD/utils.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":"43bd88e3a641a3b8"}},{"code_sha256_prefix":"180e02163f8eb159","entry":"images_to_mp4_bytes","repo":"Vchitect/Vchitect-2.0","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/Vchitect/Vchitect-2.0/blob/HEAD/utils.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":"180e02163f8eb159"}},{"code_sha256_prefix":"0aa26c53aa23a0b2","entry":"load_text_encoders","repo":"Vchitect/Vchitect-2.0","repo_kind":"listed","path":"models/pipeline.py","file_url":"https://github.com/Vchitect/Vchitect-2.0/blob/HEAD/models/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":"0aa26c53aa23a0b2"}},{"code_sha256_prefix":"f383d81f62012649","entry":"load_tf_weights_in_t5","repo":"Vchitect/Vchitect-2.0","repo_kind":"listed","path":"models/modeling_t5.py","file_url":"https://github.com/Vchitect/Vchitect-2.0/blob/HEAD/models/modeling_t5.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":"f383d81f62012649"}},{"code_sha256_prefix":"16b3184e0f465c5a","entry":"replace_all_groupnorms","repo":"Vchitect/Vchitect-2.0","repo_kind":"listed","path":"op_replace.py","file_url":"https://github.com/Vchitect/Vchitect-2.0/blob/HEAD/op_replace.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":"16b3184e0f465c5a"}},{"code_sha256_prefix":"fcac3c3ec02cb5c9","entry":"replace_all_layernorms","repo":"Vchitect/Vchitect-2.0","repo_kind":"listed","path":"op_replace.py","file_url":"https://github.com/Vchitect/Vchitect-2.0/blob/HEAD/op_replace.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":"fcac3c3ec02cb5c9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}