{"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":"/code/calculate-fid-from-inception-stats","entry":"calculate_fid_from_inception_stats","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":26,"n_papers_ran":26,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":6,"n_samples_ran":6,"n_samples_fingerprinted":0,"n_places":27,"n_places_pointer_only":16,"by_status":{"ran_honours":4,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":0},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2604.16044","paper":"/paper/arxiv-2604-16044","title":"Elucidating the SNR-t Bias of Diffusion Probabilistic Models","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"AMAP-ML/DCW","path":"fid.py","file_url":"https://github.com/AMAP-ML/DCW/blob/HEAD/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2602.19512","paper":"/paper/arxiv-2602-19512","title":"Variational Trajectory Optimization of Anisotropic Diffusion Schedules","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"lizeyu090312/anisotropic-diffusion-paper","path":"fid.py","file_url":"https://github.com/lizeyu090312/anisotropic-diffusion-paper/blob/HEAD/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2512.20233","paper":"/paper/arxiv-2512-20233","title":"How I Met Your Bias: Investigating Bias Amplification in Diffusion Models","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"NVlabs/edm","path":"fid.py","file_url":"https://github.com/NVlabs/edm/blob/HEAD/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2507.10072","paper":null,"title":"arXiv:2507.10072","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"kunzhan/wpp","path":"EDM-DWT-MM/fid.py","file_url":"https://github.com/kunzhan/wpp/blob/HEAD/EDM-DWT-MM/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2506.09376","paper":"/paper/revisiting-diffusion-models-from-generative","title":"Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation","date":"2025-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Zyriix/GDD","path":"fid.py","file_url":"https://github.com/Zyriix/GDD/blob/HEAD/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2501.15785","paper":"/paper/memorization-and-regularization-in-generative","title":"Memorization and Regularization in Generative Diffusion Models","date":"2025-01-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baptistar/DiffusionModelDynamics","path":"RectangleImages/fid.py","file_url":"https://github.com/baptistar/DiffusionModelDynamics/blob/HEAD/RectangleImages/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2412.07808","paper":"/paper/boosting-alignment-for-post-unlearning-text","title":"Boosting Alignment for Post-Unlearning Text-to-Image Generative Models","date":"2024-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"reds-lab/restricted_gradient_diversity_unlearning","path":"CIFAR/fid.py","file_url":"https://github.com/reds-lab/restricted_gradient_diversity_unlearning/blob/HEAD/CIFAR/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2410.24060","paper":"/paper/understanding-generalizability-of-diffusion","title":"Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian Structure","date":"2024-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Morefre/Understanding-Generalizability-of-Diffusion-Models-Requires-Rethinking-the-Hidden-Gaussian-Structure","path":"fid.py","file_url":"https://github.com/Morefre/Understanding-Generalizability-of-Diffusion-Models-Requires-Rethinking-the-Hidden-Gaussian-Structure/blob/HEAD/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2410.14919","paper":"/paper/adversarial-score-identity-distillation","title":"Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step","date":"2024-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingyuanzhou/sid","path":"sid_generate.py","file_url":"https://github.com/mingyuanzhou/sid/blob/HEAD/sid_generate.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"68b5e143931956cf","mcp_get_code":{"code_sha256":"68b5e143931956cf"}},{"arxiv_id":"2405.17880","paper":"/paper/diffusion-rejection-sampling","title":"Diffusion Rejection Sampling","date":"2024-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aailabkaist/DiffRS","path":"fid_npzs.py","file_url":"https://github.com/aailabkaist/DiffRS/blob/HEAD/fid_npzs.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2405.15506","paper":"/paper/learning-to-discretize-denoising-diffusion","title":"Learning to Discretize Denoising Diffusion ODEs","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vinhsuhi/ld3","path":"compute_fid.py","file_url":"https://github.com/vinhsuhi/ld3/blob/HEAD/compute_fid.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3c04e2c9c1fea67f","mcp_get_code":{"code_sha256":"3c04e2c9c1fea67f"}},{"arxiv_id":"2404.04057","paper":"/paper/score-identity-distillation-exponentially","title":"Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation","date":"2024-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingyuanzhou/SiD","path":"sid_generate.py","file_url":"https://github.com/mingyuanzhou/SiD/blob/HEAD/sid_generate.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"68b5e143931956cf","mcp_get_code":{"code_sha256":"68b5e143931956cf"}},{"arxiv_id":"2403.01189","paper":"/paper/training-unbiased-diffusion-models-from","title":"Training Unbiased Diffusion Models From Biased Dataset","date":"2024-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alsdudrla10/TIW-DSM","path":"fid.py","file_url":"https://github.com/alsdudrla10/TIW-DSM/blob/HEAD/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2310.02279","paper":"/paper/consistency-trajectory-models-learning","title":"Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion","date":"2023-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Kim-Dongjun/ctm-cifar10","path":"fid_npzs.py","file_url":"https://github.com/Kim-Dongjun/ctm-cifar10/blob/HEAD/fid_npzs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e503281a27d647f2","mcp_get_code":{"code_sha256":"e503281a27d647f2"}},{"arxiv_id":"2309.07867","paper":"/paper/beta-diffusion","title":"Beta Diffusion","date":"2023-09-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingyuanzhou/Beta-Diffusion","path":"image_experiment/fid.py","file_url":"https://github.com/mingyuanzhou/Beta-Diffusion/blob/HEAD/image_experiment/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2309.03350","paper":"/paper/relay-diffusion-unifying-diffusion-process-1","title":"Relay Diffusion: Unifying diffusion process across resolutions for image synthesis","date":"2023-09-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THUDM/RelayDiffusion","path":"evaluate.py","file_url":"https://github.com/THUDM/RelayDiffusion/blob/HEAD/evaluate.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2308.15321","paper":"/paper/elucidating-the-exposure-bias-in-diffusion","title":"Elucidating the Exposure Bias in Diffusion Models","date":"2023-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"forever208/edm-es","path":"fid.py","file_url":"https://github.com/forever208/edm-es/blob/HEAD/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2306.09305","paper":"/paper/fast-training-of-diffusion-models-with-masked","title":"Fast Training of Diffusion Models with Masked Transformers","date":"2023-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anima-lab/maskdit","path":"fid.py","file_url":"https://github.com/anima-lab/maskdit/blob/HEAD/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2306.06991","paper":"/paper/fast-diffusion-model","title":"Fast Diffusion Model","date":"2023-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/fdm","path":"fid.py","file_url":"https://github.com/sail-sg/fdm/blob/HEAD/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2305.10769","paper":"/paper/catch-up-distillation-you-only-need-to-train","title":"Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling","date":"2023-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shaoshitong/Catch-Up-Distillation","path":"fid.py","file_url":"https://github.com/shaoshitong/Catch-Up-Distillation/blob/HEAD/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2d14332c3e03501e","mcp_get_code":{"code_sha256":"2d14332c3e03501e"}},{"arxiv_id":"2304.12526","paper":"/paper/patch-diffusion-faster-and-more-data-1","title":"Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models","date":"2023-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2303.10137","paper":"/paper/a-recipe-for-watermarking-diffusion-models","title":"A Recipe for Watermarking Diffusion Models","date":"2023-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yunqing-me/watermarkdm","path":"edm/fid.py","file_url":"https://github.com/yunqing-me/watermarkdm/blob/HEAD/edm/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2302.09057","paper":"/paper/consistent-diffusion-models-mitigating-1","title":"Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent","date":"2023-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2301.12003","paper":"/paper/minimizing-trajectory-curvature-of-ode-based","title":"Minimizing Trajectory Curvature of ODE-based Generative Models","date":"2023-01-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sangyun884/fast-ode","path":"fid.py","file_url":"https://github.com/sangyun884/fast-ode/blob/HEAD/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2211.17091","paper":"/paper/refining-generative-process-with","title":"Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models","date":"2022-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2206.00364","paper":"/paper/elucidating-the-design-space-of-diffusion","title":"Elucidating the Design Space of Diffusion-Based Generative Models","date":"2022-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"45e941764344e7f3","mcp_get_code":{"code_sha256":"45e941764344e7f3"}},{"arxiv_id":"2206.00364","paper":"/paper/elucidating-the-design-space-of-diffusion","title":"Elucidating the Design Space of Diffusion-Based Generative Models","date":"2022-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"plai-group/vcdm","path":"fid.py","file_url":"https://github.com/plai-group/vcdm/blob/HEAD/fid.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"5a0fd9882013c6a5","mcp_get_code":{"code_sha256":"5a0fd9882013c6a5"}}]}