{"id":20356040,"url":"https://github.com/project-monai/generativemodels","last_synced_at":"2025-11-01T06:30:31.904Z","repository":{"id":145511349,"uuid":"536140117","full_name":"Project-MONAI/GenerativeModels","owner":"Project-MONAI","description":"MONAI Generative Models makes it easy to train, evaluate, and deploy generative models and related applications","archived":false,"fork":false,"pushed_at":"2024-07-01T14:33:54.000Z","size":14600,"stargazers_count":631,"open_issues_count":44,"forks_count":87,"subscribers_count":22,"default_branch":"main","last_synced_at":"2024-12-06T21:11:22.485Z","etag":null,"topics":["anomaly-detection","diffusion-models","generative-adversarial-network","generative-models","image-synthesis","image-translation","medical-imaging","monai","mri-reconstruction"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Project-MONAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-09-13T13:29:30.000Z","updated_at":"2024-12-06T16:28:46.000Z","dependencies_parsed_at":"2023-11-16T15:27:56.847Z","dependency_job_id":"31150b90-619c-433a-917b-9a9923403c50","html_url":"https://github.com/Project-MONAI/GenerativeModels","commit_stats":null,"previous_names":[],"tags_count":5,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Project-MONAI%2FGenerativeModels","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Project-MONAI%2FGenerativeModels/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Project-MONAI%2FGenerativeModels/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Project-MONAI%2FGenerativeModels/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Project-MONAI","download_url":"https://codeload.github.com/Project-MONAI/GenerativeModels/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239262403,"owners_count":19609519,"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":["anomaly-detection","diffusion-models","generative-adversarial-network","generative-models","image-synthesis","image-translation","medical-imaging","monai","mri-reconstruction"],"created_at":"2024-11-14T23:14:49.069Z","updated_at":"2025-02-17T09:10:47.641Z","avatar_url":"https://github.com/Project-MONAI.png","language":"Jupyter Notebook","readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://raw.githubusercontent.com/Project-MONAI/MONAI/dev/docs/images/MONAI-logo-color.png\" width=\"50%\" alt='project-monai'\u003e\n\u003c/p\u003e\n\n# MONAI Generative Models\nPrototyping repository for generative models to be integrated into MONAI core, MONAI tutorials, and MONAI model zoo.\n## Features\n* Network architectures: Diffusion Model, Autoencoder-KL, VQ-VAE, Autoregressive transformers, (Multi-scale) Patch-GAN discriminator.\n* Diffusion Model Noise Schedulers: DDPM, DDIM, and PNDM.\n* Losses: Adversarial losses, Spectral losses, and Perceptual losses (for 2D and 3D data using LPIPS, RadImageNet, and 3DMedicalNet pre-trained models).\n* Metrics: Multi-Scale Structural Similarity Index Measure (MS-SSIM) and Fréchet inception distance (FID).\n* Diffusion Models, Latent Diffusion Models, and VQ-VAE + Transformer Inferers classes (compatible with MONAI style) containing methods to train, sample synthetic images, and obtain the likelihood of inputted data.\n* MONAI-compatible trainer engine (based on Ignite) to train models with reconstruction and adversarial components.\n* Tutorials including:\n  * How to train VQ-VAEs, VQ-GANs, VQ-VAE + Transformers, AutoencoderKLs, Diffusion Models, and Latent Diffusion Models on 2D and 3D data.\n  * Train diffusion model to perform conditional image generation with classifier-free guidance.\n  * Comparison of different diffusion model schedulers.\n  * Diffusion models with different parameterizations (e.g., v-prediction and epsilon parameterization).\n  * Anomaly Detection using VQ-VAE + Transformers and Diffusion Models.\n  * Inpainting with diffusion model (using Repaint method)\n  * Super-resolution with Latent Diffusion Models (using Noise Conditioning Augmentation)\n\n## Roadmap\nOur short-term goals are available in the [Milestones](https://github.com/Project-MONAI/GenerativeModels/milestones)\nsection of the repository.\n\nIn the longer term, we aim to integrate the generative models into the MONAI core repository (supporting tasks such as,\nimage synthesis, anomaly detection, MRI reconstruction, domain transfer)\n\n## Installation\nTo install the current release of MONAI Generative Models, you can run:\n```\npip install monai-generative\n```\nTo install the current main branch of the repository, run:\n```\npip install git+https://github.com/Project-MONAI/GenerativeModels.git\n```\nRequires Python \u003e= 3.8.\n\n## Contributing\nFor guidance on making a contribution to MONAI, see the [contributing guidelines](https://github.com/Project-MONAI/GenerativeModels/blob/main/CONTRIBUTING.md).\n\n## Community\nJoin the conversation on Twitter [@ProjectMONAI](https://twitter.com/ProjectMONAI) or join our [Slack channel](https://forms.gle/QTxJq3hFictp31UM9).\n\n# Citation\n\nIf you use MONAI Generative in your research, please cite us! The citation can be exported from [the paper](https://arxiv.org/abs/2307.15208).\n\n## Links\n- Website: https://monai.io/\n- Code: https://github.com/Project-MONAI/GenerativeModels\n- Project tracker: https://github.com/Project-MONAI/GenerativeModels/projects\n- Issue tracker: https://github.com/Project-MONAI/GenerativeModels/issues\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fproject-monai%2Fgenerativemodels","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fproject-monai%2Fgenerativemodels","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fproject-monai%2Fgenerativemodels/lists"}