{"id":20207554,"url":"https://github.com/alexiajm/score_sde_fast_sampling","last_synced_at":"2025-04-10T12:34:24.711Z","repository":{"id":45802071,"uuid":"372803841","full_name":"AlexiaJM/score_sde_fast_sampling","owner":"AlexiaJM","description":"Repository for the \"Gotta Go Fast When Generating Data with Score-Based Models\" paper","archived":false,"fork":false,"pushed_at":"2021-11-20T21:59:57.000Z","size":1240,"stargazers_count":104,"open_issues_count":2,"forks_count":8,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-03-24T11:21:20.227Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AlexiaJM.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-06-01T11:22:32.000Z","updated_at":"2025-01-09T23:58:09.000Z","dependencies_parsed_at":"2022-07-17T11:47:18.496Z","dependency_job_id":null,"html_url":"https://github.com/AlexiaJM/score_sde_fast_sampling","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexiaJM%2Fscore_sde_fast_sampling","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexiaJM%2Fscore_sde_fast_sampling/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexiaJM%2Fscore_sde_fast_sampling/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexiaJM%2Fscore_sde_fast_sampling/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AlexiaJM","download_url":"https://codeload.github.com/AlexiaJM/score_sde_fast_sampling/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248217146,"owners_count":21066633,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-14T05:29:48.674Z","updated_at":"2025-04-10T12:34:24.682Z","avatar_url":"https://github.com/AlexiaJM.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Gotta Go Fast When Generating Data with Score-Based Models\n\nThis repo contains the official implementation for the paper [Gotta Go Fast When Generating Data with Score-Based Models](https://arxiv.org/abs/2105.14080), which shows how to generate data as fast as possible with score-based models using a well-designed SDE solver. See the [blog post](https://ajolicoeur.wordpress.com/gotta-go-fast-with-score-based-models/) for more details.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://i.kym-cdn.com/photos/images/newsfeed/000/615/826/8ba.gif\"\u003e\n\u003c/p\u003e\n\n--------------------\n\nThis code is a heavy modification of the [Generative Modeling through Stochastic Differential Equations repository](https://github.com/yang-song/score_sde).\n\n## 2021-09-21: Using the GottaGoFast sampler in Torch\nIf you want the PyTorch version, please use https://github.com/yang-song/score_sde_pytorch/blob/main/sde_lib.py along with my modified version of https://github.com/yang-song/score_sde_pytorch/blob/main/sampling.py which is here: https://github.com/AlexiaJM/score_sde_fast_sampling/blob/main/sde_sampling_torch.py.\n\nNotes:\n- I removed the other methods pc methods in this new file, feel free to add them back based on https://github.com/yang-song/score_sde_pytorch/blob/main/sampling.py\n- I removed a lot of options which were unnecessary from the algorithm to simplify things\n\n## To run the experiments in the paper\n\nSee the [requirements](https://github.com/AlexiaJM/score_sde_fast_sampling/blob/main/requirements.txt). \nChange the settings and folders in https://github.com/AlexiaJM/score_sde_fast_sampling/blob/main/experiments.sh and run parts of the script to run the CIFAR-10, LSUN-Church, and FFHQ experiments.\n\nThe SDE solver can be found [here](https://github.com/AlexiaJM/score_sde_fast_sampling/blob/main/sampling.py#L172) and the loop [here](https://github.com/AlexiaJM/score_sde_fast_sampling/blob/main/sampling.py#L574).\n\n## For general usage \n\nPlease refer to the [original code](https://github.com/yang-song/score_sde).\n\n## Pretrained checkpoints\n\nhttps://drive.google.com/drive/folders/10pQygNzF7hOOLwP3q8GiNxSnFRpArUxQ?usp=sharing\n\n## References\nIf you find the code useful for your research, please consider citing\n```bib\n@article{jolicoeurmartineau2021gotta,\n      title={Gotta Go Fast When Generating Data with Score-Based Models}, \n      author={Alexia Jolicoeur-Martineau and Ke Li and R{\\'e}mi Pich{\\'e}-Taillefer and Tal Kachman and Ioannis Mitliagkas},\n      journal={arXiv preprint arXiv:2105.14080},\n      year={2021}\n}\n```\nand \n```bib\n@inproceedings{\n  song2021scorebased,\n  title={Score-Based Generative Modeling through Stochastic Differential Equations},\n  author={Yang Song and Jascha Sohl-Dickstein and Diederik P Kingma and Abhishek Kumar and Stefano Ermon and Ben Poole},\n  booktitle={International Conference on Learning Representations},\n  year={2021},\n  url={https://openreview.net/forum?id=PxTIG12RRHS}\n}\n```\n\nOfficial theme song can be found here: https://soundcloud.com/emyaze/gotta-go-fast.\n\n## Samples (see the paper for more samples)\n\n![](/images/both.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falexiajm%2Fscore_sde_fast_sampling","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falexiajm%2Fscore_sde_fast_sampling","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falexiajm%2Fscore_sde_fast_sampling/lists"}