{"id":48839700,"url":"https://github.com/smsharma/minified-generative-models","last_synced_at":"2026-04-15T01:03:41.659Z","repository":{"id":181724729,"uuid":"609721512","full_name":"smsharma/minified-generative-models","owner":"smsharma","description":"Bare-bones implementations of some generative models in Jax: diffusion, normalizing flows, consistency models, flow matching, (beta)-VAEs, etc","archived":false,"fork":false,"pushed_at":"2023-12-20T17:28:04.000Z","size":12608,"stargazers_count":37,"open_issues_count":0,"forks_count":5,"subscribers_count":4,"default_branch":"main","last_synced_at":"2024-04-17T14:09:54.483Z","etag":null,"topics":["consistency-models","diffusion-models","flow-matching","generative-models","minified","neural-compression","normalizing-flows","variational-autoencoder"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/smsharma.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2023-03-05T02:55:11.000Z","updated_at":"2024-04-05T20:57:27.000Z","dependencies_parsed_at":"2023-12-20T18:35:07.964Z","dependency_job_id":null,"html_url":"https://github.com/smsharma/minified-generative-models","commit_stats":null,"previous_names":["smsharma/minified-generative-models"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/smsharma/minified-generative-models","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smsharma%2Fminified-generative-models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smsharma%2Fminified-generative-models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smsharma%2Fminified-generative-models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smsharma%2Fminified-generative-models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/smsharma","download_url":"https://codeload.github.com/smsharma/minified-generative-models/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/smsharma%2Fminified-generative-models/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31821686,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-14T18:05:02.291Z","status":"ssl_error","status_checked_at":"2026-04-14T18:05:01.765Z","response_time":153,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["consistency-models","diffusion-models","flow-matching","generative-models","minified","neural-compression","normalizing-flows","variational-autoencoder"],"created_at":"2026-04-15T01:03:41.027Z","updated_at":"2026-04-15T01:03:41.646Z","avatar_url":"https://github.com/smsharma.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Minified generative models\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-red.svg)](https://opensource.org/licenses/MIT)\n\nBare-bones, minified versions of some common (and not-so-common) generative models, for pedagogical purposes.\n\n## Installation\n\nFirst, install JAX following these [instructions](https://jax.readthedocs.io/en/latest/installation.html). For CPU-only, this is as simple as:\n```bash\npip install \"jax[cpu]\"\n```\nAdditional libraries:\n```bash\npip install flax optax diffrax tensorflow_probability scikit-learn tqdm matplotlib\n```\n\n## List of notebooks\n\n1. [β-VAEs](01_beta_vae.ipynb): Variational autoencoders and basic rate-distortion theory.\n2. [Diffusion models](02_diffusion.ipynb): Diffusion models, covering likelihood-based and score-matching interpretations.\n3. [Normalizing flows](03_normalizing_flows.ipynb) (WiP annotations): Normalizing flows, specifically [RealNVP](https://arxiv.org/abs/1605.08803).\n4. [Continuous normalizing flows](03_continuous_normalizing_flows.ipynb): Continuous-time normalizing flows from e.g., [Grathwohl et al 2018](https://arxiv.org/abs/1810.01367).\n5. [Consistency models](04_consistency_models.ipynb) (WiP annotations): Consistency models from [Song et al 2023](https://arxiv.org/abs/2303.01469).\n6. [Flow matching](05_flow_matching.ipynb) (WiP annotations): From [Lipman et al 2022](https://arxiv.org/abs/2210.02747); see also [Albergo et al 2023](https://arxiv.org/abs/2303.08797).\n7. [Diffusion distillation](06_diffusion_distillation.ipynb) (WiP): Progressive ([Salimans et al 2022](https://arxiv.org/abs/2202.00512)) and consistency ([Song et al 2023](https://arxiv.org/abs/2303.01469)) distillation.\n8. [Discrete walk-jump sampling](07_discrete_walk_jump_sampling.ipynb) (WiP): From [Frey et al 2023](https://arxiv.org/abs/2306.12360).\n\n## Inspiration\n\n![assets/midwit.pngs](assets/midwit.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsmsharma%2Fminified-generative-models","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsmsharma%2Fminified-generative-models","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsmsharma%2Fminified-generative-models/lists"}