{"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/revisiting-diffusion-models-from-generative","title":"Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation","arxiv_id":"2506.09376","date":"2025-06-11","proceeding":null,"authors":["Bowen Zheng","Tianming Yang"],"abstract":"Diffusion distillation is a widely used technique to reduce the sampling cost of diffusion models, yet it often requires extensive training, and the student performance tends to be degraded. Recent studies show that incorporating a GAN objective may alleviate these issues, yet the underlying mechanism remains unclear. In this work, we first identify a key limitation of distillation: mismatched step sizes and parameter numbers between the teacher and the student model lead them to converge to different local minima, rendering direct imitation suboptimal. We further demonstrate that a standalone GAN objective, without relying a distillation loss, overcomes this limitation and is sufficient to convert diffusion models into efficient one-step generators. Based on this finding, we propose that diffusion training may be viewed as a form of generative pre-training, equipping models with capabilities that can be unlocked through lightweight GAN fine-tuning. Supporting this view, we create a one-step generation model by fine-tuning a pre-trained model with 85% of parameters frozen, achieving strong performance with only 0.2M images and near-SOTA results with 5M images. We further present a frequency-domain analysis that may explain the one-step generative capability gained in diffusion training. Overall, our work provides a new perspective for diffusion training, highlighting its role as a powerful generative pre-training process, which can be the basis for building efficient one-step generation models.","url_abs":"https://arxiv.org/abs/2506.09376v1","url_pdf":"https://arxiv.org/pdf/2506.09376v1.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":"revisiting-diffusion-models-from-generative","repo_url":"https://github.com/Zyriix/GDD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.09376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.09376"}},"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/Zyriix/GDD","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4,"ran":3,"ran_honours":1,"ran_fixture":1,"unverified":5},"by_repo_kind":{"listed":{"samples":14,"ran":9,"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":"ef1e7dffb5d433d4","entry":"NormLayer","repo":"Zyriix/GDD","repo_kind":"listed","path":"pg_modules/blocks.py","file_url":"https://github.com/Zyriix/GDD/blob/HEAD/pg_modules/blocks.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":"ef1e7dffb5d433d4"}},{"code_sha256_prefix":"f87cd99314206f72","entry":"UpBlockBig","repo":"Zyriix/GDD","repo_kind":"listed","path":"pg_modules/blocks.py","file_url":"https://github.com/Zyriix/GDD/blob/HEAD/pg_modules/blocks.py","link_basis":"harvester_set","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":"Zyriix/GDD","repo_kind":"listed","path":"pg_modules/blocks.py","file_url":"https://github.com/Zyriix/GDD/blob/HEAD/pg_modules/blocks.py","link_basis":"harvester_set","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":"45e941764344e7f3","entry":"calculate_fid_from_inception_stats","repo":"Zyriix/GDD","repo_kind":"listed","path":"fid.py","file_url":"https://github.com/Zyriix/GDD/blob/HEAD/fid.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"code_sha256_prefix":"674eca7b9e1b6439","entry":"format_time","repo":"Zyriix/GDD","repo_kind":"listed","path":"dnnlib/util.py","file_url":"https://github.com/Zyriix/GDD/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":"Zyriix/GDD","repo_kind":"listed","path":"dnnlib/util.py","file_url":"https://github.com/Zyriix/GDD/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":"Zyriix/GDD","repo_kind":"listed","path":"feature_networks/vit.py","file_url":"https://github.com/Zyriix/GDD/blob/HEAD/feature_networks/vit.py","link_basis":"harvester_set","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":"Zyriix/GDD","repo_kind":"listed","path":"feature_networks/vit.py","file_url":"https://github.com/Zyriix/GDD/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":"d41a4250066bce93","entry":"weight_init","repo":"Zyriix/GDD","repo_kind":"listed","path":"training/networks.py","file_url":"https://github.com/Zyriix/GDD/blob/HEAD/training/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":"Zyriix/GDD","repo_kind":"listed","path":"dnnlib/util.py","file_url":"https://github.com/Zyriix/GDD/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":"77de35b318b043bc","entry":"edm_sampler","repo":"Zyriix/GDD","repo_kind":"listed","path":"generate.py","file_url":"https://github.com/Zyriix/GDD/blob/HEAD/generate.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":"77de35b318b043bc"}},{"code_sha256_prefix":"4c52162336ee4320","entry":"forward_vit","repo":"Zyriix/GDD","repo_kind":"listed","path":"feature_networks/vit.py","file_url":"https://github.com/Zyriix/GDD/blob/HEAD/feature_networks/vit.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":"4c52162336ee4320"}},{"code_sha256_prefix":"0be9e03ad996ebbc","entry":"one_step_sampler","repo":"Zyriix/GDD","repo_kind":"listed","path":"generate.py","file_url":"https://github.com/Zyriix/GDD/blob/HEAD/generate.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":"0be9e03ad996ebbc"}},{"code_sha256_prefix":"16be42f0d2cefcd0","entry":"two_step_sampler","repo":"Zyriix/GDD","repo_kind":"listed","path":"generate.py","file_url":"https://github.com/Zyriix/GDD/blob/HEAD/generate.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":"16be42f0d2cefcd0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}