{"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/make-a-cheap-scaling-a-self-cascade-diffusion","title":"Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation","arxiv_id":"2402.10491","date":"2024-02-16","proceeding":null,"authors":["Lanqing Guo","Yingqing He","Haoxin Chen","Menghan Xia","Xiaodong Cun","YuFei Wang","Siyu Huang","Yong Zhang","Xintao Wang","Qifeng Chen","Ying Shan","Bihan Wen"],"abstract":"Diffusion models have proven to be highly effective in image and video generation; however, they still face composition challenges when generating images of varying sizes due to single-scale training data. Adapting large pre-trained diffusion models for higher resolution demands substantial computational and optimization resources, yet achieving a generation capability comparable to low-resolution models remains elusive. This paper proposes a novel self-cascade diffusion model that leverages the rich knowledge gained from a well-trained low-resolution model for rapid adaptation to higher-resolution image and video generation, employing either tuning-free or cheap upsampler tuning paradigms. Integrating a sequence of multi-scale upsampler modules, the self-cascade diffusion model can efficiently adapt to a higher resolution, preserving the original composition and generation capabilities. We further propose a pivot-guided noise re-schedule strategy to speed up the inference process and improve local structural details. Compared to full fine-tuning, our approach achieves a 5X training speed-up and requires only an additional 0.002M tuning parameters. Extensive experiments demonstrate that our approach can quickly adapt to higher resolution image and video synthesis by fine-tuning for just 10k steps, with virtually no additional inference time.","url_abs":"https://arxiv.org/abs/2402.10491v1","url_pdf":"https://arxiv.org/pdf/2402.10491v1.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":"make-a-cheap-scaling-a-self-cascade-diffusion","repo_url":"https://github.com/guolanqing/self-cascade","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.10491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10491"}},"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/guolanqing/self-cascade","reach":{"status":"ok"}}],"summary":{"ran":4,"ran_violates":1,"ran_draft_wrong":3},"by_repo_kind":{"official":{"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":"8f92deb310eb9332","entry":"collate_fn","repo":"guolanqing/self-cascade","repo_kind":"official","path":"sdxl_main.py","file_url":"https://github.com/guolanqing/self-cascade/blob/HEAD/sdxl_main.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":"8f92deb310eb9332"}},{"code_sha256_prefix":"ac4dc60b24a6d082","entry":"collate_fn","repo":"guolanqing/self-cascade","repo_kind":"official","path":"sdxl_main_4x_2nodes.py","file_url":"https://github.com/guolanqing/self-cascade/blob/HEAD/sdxl_main_4x_2nodes.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":"ac4dc60b24a6d082"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"guolanqing/self-cascade","repo_kind":"official","path":"source_override/ldm/attention.py","file_url":"https://github.com/guolanqing/self-cascade/blob/HEAD/source_override/ldm/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"9a64f76511f799c6","entry":"make_grid_np","repo":"guolanqing/self-cascade","repo_kind":"official","path":"source_override/ldm/attention.py","file_url":"https://github.com/guolanqing/self-cascade/blob/HEAD/source_override/ldm/attention.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":"9a64f76511f799c6"}},{"code_sha256_prefix":"bea2d776a332f2b0","entry":"rescale_noise_cfg","repo":"guolanqing/self-cascade","repo_kind":"official","path":"source_override/pipeline_sdxl.py","file_url":"https://github.com/guolanqing/self-cascade/blob/HEAD/source_override/pipeline_sdxl.py","link_basis":"harvester_set","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":"bea2d776a332f2b0"}},{"code_sha256_prefix":"0f720088a60b7826","entry":"resize_image_keeping_aspect_ratio","repo":"guolanqing/self-cascade","repo_kind":"official","path":"sdxl_main.py","file_url":"https://github.com/guolanqing/self-cascade/blob/HEAD/sdxl_main.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":"0f720088a60b7826"}},{"code_sha256_prefix":"22b1f260da28f6a5","entry":"retrieve_timesteps","repo":"guolanqing/self-cascade","repo_kind":"official","path":"source_override/pipeline_sdxl.py","file_url":"https://github.com/guolanqing/self-cascade/blob/HEAD/source_override/pipeline_sdxl.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"22b1f260da28f6a5"}},{"code_sha256_prefix":"9a299fe5ae09e407","entry":"uniq","repo":"guolanqing/self-cascade","repo_kind":"official","path":"source_override/ldm/attention.py","file_url":"https://github.com/guolanqing/self-cascade/blob/HEAD/source_override/ldm/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9a299fe5ae09e407"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}