{"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/progressive-autoregressive-video-diffusion","title":"Progressive Autoregressive Video Diffusion Models","arxiv_id":"2410.08151","date":"2024-10-10","proceeding":null,"authors":["Desai Xie","Zhan Xu","Yicong Hong","Hao Tan","Difan Liu","Feng Liu","Arie Kaufman","Yang Zhou"],"abstract":"Current frontier video diffusion models have demonstrated remarkable results at generating high-quality videos. However, they can only generate short video clips, normally around 10 seconds or 240 frames, due to computation limitations during training. Existing methods naively achieve autoregressive long video generation by directly placing the ending of the previous clip at the front of the attention window as conditioning, which leads to abrupt scene changes, unnatural motion, and error accumulation. In this work, we introduce a more natural formulation of autoregressive long video generation by revisiting the noise level assumption in video diffusion models. Our key idea is to 1. assign the frames with per-frame, progressively increasing noise levels rather than a single noise level and 2. denoise and shift the frames in small intervals rather than all at once. This allows for smoother attention correspondence among frames with adjacent noise levels, larger overlaps between the attention windows, and better propagation of information from the earlier to the later frames. Video diffusion models equipped with our progressive noise schedule can autoregressively generate long videos with much improved fidelity compared to the baselines and minimal quality degradation over time. We present the first results on text-conditioned 60-second (1440 frames) long video generation at a quality close to frontier models. Code and video results are available at https://desaixie.github.io/pa-vdm/.","url_abs":"https://arxiv.org/abs/2410.08151v2","url_pdf":"https://arxiv.org/pdf/2410.08151v2.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":"progressive-autoregressive-video-diffusion","repo_url":"https://github.com/desaixie/pa_vdm","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"video-denoising","task_name":"Video Denoising"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2410.08151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08151"}},"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/desaixie/pa_vdm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":"af810cd485700e94","entry":"build_module","repo":"desaixie/pa_vdm","repo_kind":"official","path":"opensora/registry.py","file_url":"https://github.com/desaixie/pa_vdm/blob/HEAD/opensora/registry.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":"af810cd485700e94"}},{"code_sha256_prefix":"1d84e2bdaf34e46f","entry":"calculate_psnr","repo":"desaixie/pa_vdm","repo_kind":"official","path":"eval/vae/cal_psnr.py","file_url":"https://github.com/desaixie/pa_vdm/blob/HEAD/eval/vae/cal_psnr.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":"1d84e2bdaf34e46f"}},{"code_sha256_prefix":"3bdf7dc84b510bf0","entry":"calculate_ssim_function","repo":"desaixie/pa_vdm","repo_kind":"official","path":"eval/vae/cal_ssim.py","file_url":"https://github.com/desaixie/pa_vdm/blob/HEAD/eval/vae/cal_ssim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3bdf7dc84b510bf0"}},{"code_sha256_prefix":"5a1fb9d13411a6e9","entry":"img_psnr","repo":"desaixie/pa_vdm","repo_kind":"official","path":"eval/vae/cal_psnr.py","file_url":"https://github.com/desaixie/pa_vdm/blob/HEAD/eval/vae/cal_psnr.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":"5a1fb9d13411a6e9"}},{"code_sha256_prefix":"897aa81e3eb07ee1","entry":"ssim","repo":"desaixie/pa_vdm","repo_kind":"official","path":"eval/vae/cal_ssim.py","file_url":"https://github.com/desaixie/pa_vdm/blob/HEAD/eval/vae/cal_ssim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"897aa81e3eb07ee1"}},{"code_sha256_prefix":"a0bb3768ee24ee05","entry":"trans","repo":"desaixie/pa_vdm","repo_kind":"official","path":"eval/vae/cal_lpips.py","file_url":"https://github.com/desaixie/pa_vdm/blob/HEAD/eval/vae/cal_lpips.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":"a0bb3768ee24ee05"}},{"code_sha256_prefix":"4f6235b68bad4f04","entry":"trans","repo":"desaixie/pa_vdm","repo_kind":"official","path":"eval/vae/cal_flolpips.py","file_url":"https://github.com/desaixie/pa_vdm/blob/HEAD/eval/vae/cal_flolpips.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":"4f6235b68bad4f04"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}