{"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/pfgm-unlocking-the-potential-of-physics","title":"PFGM++: Unlocking the Potential of Physics-Inspired Generative Models","arxiv_id":"2302.04265","date":"2023-02-08","proceeding":null,"authors":["Yilun Xu","Ziming Liu","Yonglong Tian","Shangyuan Tong","Max Tegmark","Tommi Jaakkola"],"abstract":"We introduce a new family of physics-inspired generative models termed PFGM++ that unifies diffusion models and Poisson Flow Generative Models (PFGM). These models realize generative trajectories for $N$ dimensional data by embedding paths in $N{+}D$ dimensional space while still controlling the progression with a simple scalar norm of the $D$ additional variables. The new models reduce to PFGM when $D{=}1$ and to diffusion models when $D{\\to}\\infty$. The flexibility of choosing $D$ allows us to trade off robustness against rigidity as increasing $D$ results in more concentrated coupling between the data and the additional variable norms. We dispense with the biased large batch field targets used in PFGM and instead provide an unbiased perturbation-based objective similar to diffusion models. To explore different choices of $D$, we provide a direct alignment method for transferring well-tuned hyperparameters from diffusion models ($D{\\to} \\infty$) to any finite $D$ values. Our experiments show that models with finite $D$ can be superior to previous state-of-the-art diffusion models on CIFAR-10/FFHQ $64{\\times}64$ datasets, with FID scores of $1.91/2.43$ when $D{=}2048/128$. In class-conditional setting, $D{=}2048$ yields current state-of-the-art FID of $1.74$ on CIFAR-10. In addition, we demonstrate that models with smaller $D$ exhibit improved robustness against modeling errors. Code is available at https://github.com/Newbeeer/pfgmpp","url_abs":"https://arxiv.org/abs/2302.04265v2","url_pdf":"https://arxiv.org/pdf/2302.04265v2.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":"pfgm-unlocking-the-potential-of-physics","repo_url":"https://github.com/newbeeer/pfgmpp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"2048","task_name":"Playing the Game of 2048"}],"methods":[{"method_slug":"pfgm","method_name":"PFGM"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-cifar-10","task":"Image Generation","dataset":"CIFAR-10","model":"PFGM++","rank_in_archive_order":9,"of":78,"metrics":{"FID":"1.74"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-ffhq-64x64-4x-upscaling","task":"Image Generation","dataset":"FFHQ 64x64 - 4x upscaling","model":"PFGM++","rank_in_archive_order":1,"of":1,"metrics":{"FID":"2.43"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.04265","atlas_url":"https://app.syntology.ai/?focus=2302.04265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.04265"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/newbeeer/pfgmpp","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":3,"samples":[{"code_sha256_prefix":"1a497dc67152411a","entry":"edm_sampler","repo":"newbeeer/pfgmpp","repo_kind":"official","path":"generate.py","file_url":"https://github.com/newbeeer/pfgmpp/blob/HEAD/generate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1a497dc67152411a"}},{"code_sha256_prefix":"cacd4f6ec202d9b4","entry":"parse_int_list","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"cacd4f6ec202d9b4"}},{"code_sha256_prefix":"daa5186ef7b993ca","entry":"ablation_sampler","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"daa5186ef7b993ca"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}