{"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/pagoda-progressive-growing-of-a-one-step","title":"PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher","arxiv_id":"2405.14822","date":"2024-05-23","proceeding":null,"authors":["Dongjun Kim","Chieh-Hsin Lai","Wei-Hsiang Liao","Yuhta Takida","Naoki Murata","Toshimitsu Uesaka","Yuki Mitsufuji","Stefano Ermon"],"abstract":"The diffusion model performs remarkable in generating high-dimensional content but is computationally intensive, especially during training. We propose Progressive Growing of Diffusion Autoencoder (PaGoDA), a novel pipeline that reduces the training costs through three stages: training diffusion on downsampled data, distilling the pretrained diffusion, and progressive super-resolution. With the proposed pipeline, PaGoDA achieves a $64\\times$ reduced cost in training its diffusion model on 8x downsampled data; while at the inference, with the single-step, it performs state-of-the-art on ImageNet across all resolutions from 64x64 to 512x512, and text-to-image. PaGoDA's pipeline can be applied directly in the latent space, adding compression alongside the pre-trained autoencoder in Latent Diffusion Models (e.g., Stable Diffusion). The code is available at https://github.com/sony/pagoda.","url_abs":"https://arxiv.org/abs/2405.14822v2","url_pdf":"https://arxiv.org/pdf/2405.14822v2.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":"pagoda-progressive-growing-of-a-one-step","repo_url":"https://github.com/sony/pagoda","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-imagenet-128x128","task":"Image Generation","dataset":"ImageNet 128x128","model":"PaGoDA","rank_in_archive_order":2,"of":23,"metrics":{"FID":"1.48"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-imagenet-256x256","task":"Image Generation","dataset":"ImageNet 256x256","model":"PaGoDA","rank_in_archive_order":25,"of":94,"metrics":{"FID":"1.56"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-imagenet-32x32","task":"Image Generation","dataset":"ImageNet 32x32","model":"PaGoDA","rank_in_archive_order":1,"of":35,"metrics":{"FID":"0.79"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-imagenet-512x512","task":"Image Generation","dataset":"ImageNet 512x512","model":"PaGoDA","rank_in_archive_order":19,"of":52,"metrics":{"FID":"1.80"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-imagenet-64x64","task":"Image Generation","dataset":"ImageNet 64x64","model":"PaGoDA","rank_in_archive_order":6,"of":65,"metrics":{"FID":"1.21","Inception Score":"76.47","NFE":"1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.14822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14822"}},"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":"deterministic:regex_extraction","url":"https://github.com/sony/pagoda","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":3,"ran_draft_wrong":8,"ran":3,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":17,"ran":15,"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":"30befb7e4327e615","entry":"append_dims","repo":"sony/pagoda","repo_kind":"official","path":"data_gather_reverse.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/data_gather_reverse.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"30befb7e4327e615"}},{"code_sha256_prefix":"ef1e7dffb5d433d4","entry":"NormLayer","repo":"sony/pagoda","repo_kind":"official","path":"pg_modules/blocks.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/pg_modules/blocks.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef1e7dffb5d433d4"}},{"code_sha256_prefix":"9fcdaa6e423e8aa7","entry":"Normalize","repo":"sony/pagoda","repo_kind":"official","path":"cm/sd_model.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/cm/sd_model.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9fcdaa6e423e8aa7"}},{"code_sha256_prefix":"f87cd99314206f72","entry":"UpBlockBig","repo":"sony/pagoda","repo_kind":"official","path":"pg_modules/blocks.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/pg_modules/blocks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f87cd99314206f72"}},{"code_sha256_prefix":"0186912dcb8b92b9","entry":"UpBlockSmall","repo":"sony/pagoda","repo_kind":"official","path":"pg_modules/blocks.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/pg_modules/blocks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0186912dcb8b92b9"}},{"code_sha256_prefix":"cfd76fd0d89574a4","entry":"approx_standard_normal_cdf","repo":"sony/pagoda","repo_kind":"official","path":"cm/losses.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/cm/losses.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cfd76fd0d89574a4"}},{"code_sha256_prefix":"cd33283d615fb3d7","entry":"discretized_gaussian_log_likelihood","repo":"sony/pagoda","repo_kind":"official","path":"cm/losses.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/cm/losses.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cd33283d615fb3d7"}},{"code_sha256_prefix":"674eca7b9e1b6439","entry":"format_time","repo":"sony/pagoda","repo_kind":"official","path":"dnnlib/util.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/dnnlib/util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"674eca7b9e1b6439"}},{"code_sha256_prefix":"32af001972a0699f","entry":"format_time_brief","repo":"sony/pagoda","repo_kind":"official","path":"dnnlib/util.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/dnnlib/util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32af001972a0699f"}},{"code_sha256_prefix":"562cccfa5027f008","entry":"forward_flex","repo":"sony/pagoda","repo_kind":"official","path":"feature_networks/vit.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/feature_networks/vit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"562cccfa5027f008"}},{"code_sha256_prefix":"1c094193a4506a40","entry":"get_activation","repo":"sony/pagoda","repo_kind":"official","path":"feature_networks/vit.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/feature_networks/vit.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1c094193a4506a40"}},{"code_sha256_prefix":"cb49209c125de1b4","entry":"get_timestep_embedding","repo":"sony/pagoda","repo_kind":"official","path":"cm/sd_model.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/cm/sd_model.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb49209c125de1b4"}},{"code_sha256_prefix":"3137073275f8c21a","entry":"nonlinearity","repo":"sony/pagoda","repo_kind":"official","path":"cm/sd_model.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/cm/sd_model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3137073275f8c21a"}},{"code_sha256_prefix":"cf2798b666b231ca","entry":"normal_kl","repo":"sony/pagoda","repo_kind":"official","path":"cm/losses.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/cm/losses.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cf2798b666b231ca"}},{"code_sha256_prefix":"d41a4250066bce93","entry":"weight_init","repo":"sony/pagoda","repo_kind":"official","path":"cm/networks.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/cm/networks.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d41a4250066bce93"}},{"code_sha256_prefix":"9d31d2c4cd16bb2d","entry":"ask_yes_no","repo":"sony/pagoda","repo_kind":"official","path":"dnnlib/util.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/dnnlib/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9d31d2c4cd16bb2d"}},{"code_sha256_prefix":"4c52162336ee4320","entry":"forward_vit","repo":"sony/pagoda","repo_kind":"official","path":"feature_networks/vit.py","file_url":"https://github.com/sony/pagoda/blob/HEAD/feature_networks/vit.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4c52162336ee4320"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}