{"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/flashvideo-flowing-fidelity-to-detail-for","title":"FlashVideo:Flowing Fidelity to Detail for Efficient High-Resolution Video Generation","arxiv_id":"2502.05179","date":"2025-02-07","proceeding":null,"authors":["Shilong Zhang","Wenbo Li","Shoufa Chen","Chongjian Ge","Peize Sun","Yida Zhang","Yi Jiang","Zehuan Yuan","Binyue Peng","Ping Luo"],"abstract":"DiT diffusion models have achieved great success in text-to-video generation, leveraging their scalability in model capacity and data scale. High content and motion fidelity aligned with text prompts, however, often require large model parameters and a substantial number of function evaluations (NFEs). Realistic and visually appealing details are typically reflected in high resolution outputs, further amplifying computational demands especially for single stage DiT models. To address these challenges, we propose a novel two stage framework, FlashVideo, which strategically allocates model capacity and NFEs across stages to balance generation fidelity and quality. In the first stage, prompt fidelity is prioritized through a low resolution generation process utilizing large parameters and sufficient NFEs to enhance computational efficiency. The second stage establishes flow matching between low and high resolutions, effectively generating fine details with minimal NFEs. Quantitative and visual results demonstrate that FlashVideo achieves state-of-the-art high resolution video generation with superior computational efficiency. Additionally, the two-stage design enables users to preview the initial output before committing to full resolution generation, thereby significantly reducing computational costs and wait times as well as enhancing commercial viability .","url_abs":"https://arxiv.org/abs/2502.05179v1","url_pdf":"https://arxiv.org/pdf/2502.05179v1.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":"flashvideo-flowing-fidelity-to-detail-for","repo_url":"https://github.com/foundationvision/flashvideo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"text-to-video-generation","task_name":"Text-to-Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.05179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05179"}},"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/foundationvision/flashvideo","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_honours":1,"ran_violates":3,"ran":1,"ran_draft_wrong":1,"unverified":9},"by_repo_kind":{"official":{"samples":15,"ran":6,"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":"c1b68cdd9e73316a","entry":"cast_tuple","repo":"foundationvision/flashvideo","repo_kind":"official","path":"flashvideo/vae_modules/cp_enc_dec.py","file_url":"https://github.com/foundationvision/flashvideo/blob/HEAD/flashvideo/vae_modules/cp_enc_dec.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c1b68cdd9e73316a"}},{"code_sha256_prefix":"424012cb37b31172","entry":"default","repo":"foundationvision/flashvideo","repo_kind":"official","path":"flashvideo/vae_modules/attention.py","file_url":"https://github.com/foundationvision/flashvideo/blob/HEAD/flashvideo/vae_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":"f912c209e9c899ca","entry":"divisible_by","repo":"foundationvision/flashvideo","repo_kind":"official","path":"flashvideo/vae_modules/cp_enc_dec.py","file_url":"https://github.com/foundationvision/flashvideo/blob/HEAD/flashvideo/vae_modules/cp_enc_dec.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f912c209e9c899ca"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"foundationvision/flashvideo","repo_kind":"official","path":"flashvideo/vae_modules/attention.py","file_url":"https://github.com/foundationvision/flashvideo/blob/HEAD/flashvideo/vae_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":"6686c8acf02ec831","entry":"get_unique_embedder_keys_from_conditioner","repo":"foundationvision/flashvideo","repo_kind":"official","path":"flashvideo/utils.py","file_url":"https://github.com/foundationvision/flashvideo/blob/HEAD/flashvideo/utils.py","link_basis":"harvester_set","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":"6686c8acf02ec831"}},{"code_sha256_prefix":"9a299fe5ae09e407","entry":"uniq","repo":"foundationvision/flashvideo","repo_kind":"official","path":"flashvideo/vae_modules/attention.py","file_url":"https://github.com/foundationvision/flashvideo/blob/HEAD/flashvideo/vae_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":"96d9af18b865527c","entry":"add_extra_config_args","repo":"foundationvision/flashvideo","repo_kind":"official","path":"flashvideo/arguments.py","file_url":"https://github.com/foundationvision/flashvideo/blob/HEAD/flashvideo/arguments.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":"96d9af18b865527c"}},{"code_sha256_prefix":"165540c4cfc6fce1","entry":"add_model_config_args","repo":"foundationvision/flashvideo","repo_kind":"official","path":"flashvideo/arguments.py","file_url":"https://github.com/foundationvision/flashvideo/blob/HEAD/flashvideo/arguments.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":"165540c4cfc6fce1"}},{"code_sha256_prefix":"63a18d6c97fa3300","entry":"add_sampling_config_args","repo":"foundationvision/flashvideo","repo_kind":"official","path":"flashvideo/arguments.py","file_url":"https://github.com/foundationvision/flashvideo/blob/HEAD/flashvideo/arguments.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":"63a18d6c97fa3300"}},{"code_sha256_prefix":"c0aeee5806437317","entry":"decode","repo":"foundationvision/flashvideo","repo_kind":"official","path":"flashvideo/utils.py","file_url":"https://github.com/foundationvision/flashvideo/blob/HEAD/flashvideo/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":"c0aeee5806437317"}},{"code_sha256_prefix":"cdd29f549144d05e","entry":"get_2d_sincos_pos_embed","repo":"foundationvision/flashvideo","repo_kind":"official","path":"flashvideo/dit_video_concat.py","file_url":"https://github.com/foundationvision/flashvideo/blob/HEAD/flashvideo/dit_video_concat.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":"cdd29f549144d05e"}},{"code_sha256_prefix":"665d8a4e8f673a4c","entry":"get_2d_sincos_pos_embed_from_grid","repo":"foundationvision/flashvideo","repo_kind":"official","path":"flashvideo/dit_video_concat.py","file_url":"https://github.com/foundationvision/flashvideo/blob/HEAD/flashvideo/dit_video_concat.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":"665d8a4e8f673a4c"}},{"code_sha256_prefix":"7759e9a501ea471a","entry":"get_3d_sincos_pos_embed","repo":"foundationvision/flashvideo","repo_kind":"official","path":"flashvideo/dit_video_concat.py","file_url":"https://github.com/foundationvision/flashvideo/blob/HEAD/flashvideo/dit_video_concat.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":"7759e9a501ea471a"}},{"code_sha256_prefix":"1bd867ae3eda28ff","entry":"get_batch","repo":"foundationvision/flashvideo","repo_kind":"official","path":"flashvideo/utils.py","file_url":"https://github.com/foundationvision/flashvideo/blob/HEAD/flashvideo/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":"1bd867ae3eda28ff"}},{"code_sha256_prefix":"945442cc2f6a19c9","entry":"is_odd","repo":"foundationvision/flashvideo","repo_kind":"official","path":"flashvideo/vae_modules/cp_enc_dec.py","file_url":"https://github.com/foundationvision/flashvideo/blob/HEAD/flashvideo/vae_modules/cp_enc_dec.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":"945442cc2f6a19c9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}