{"id":13478313,"url":"https://github.com/tcapelle/cloud_diffusion","last_synced_at":"2025-04-13T13:26:47.203Z","repository":{"id":137007981,"uuid":"612185706","full_name":"tcapelle/cloud_diffusion","owner":"tcapelle","description":"Diffusion on the Clouds: Short-term solar energy forecasting with Diffusion Models","archived":false,"fork":false,"pushed_at":"2024-03-21T20:24:13.000Z","size":13215,"stargazers_count":42,"open_issues_count":0,"forks_count":11,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-24T09:41:30.547Z","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/tcapelle.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,"governance":null,"roadmap":null,"authors":null}},"created_at":"2023-03-10T11:37:45.000Z","updated_at":"2025-02-16T09:42:06.000Z","dependencies_parsed_at":null,"dependency_job_id":"f6b4cd06-8034-4803-b678-491554f29086","html_url":"https://github.com/tcapelle/cloud_diffusion","commit_stats":null,"previous_names":[],"tags_count":7,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tcapelle%2Fcloud_diffusion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tcapelle%2Fcloud_diffusion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tcapelle%2Fcloud_diffusion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tcapelle%2Fcloud_diffusion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tcapelle","download_url":"https://codeload.github.com/tcapelle/cloud_diffusion/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248719625,"owners_count":21150774,"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":"2024-07-31T16:01:55.393Z","updated_at":"2025-04-13T13:26:47.179Z","avatar_url":"https://github.com/tcapelle.png","language":"Python","readme":"[![](https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-gradient.svg)](https://wandb.ai/capecape/ddpm_clouds/reports/Diffusion-on-the-Clouds-Short-term-solar-energy-forecasting-with-Diffusion-Models--VmlldzozNDMxNTg5)\n[![PyPI version](https://badge.fury.io/py/cloud_diffusion.svg)](https://badge.fury.io/py/cloud_diffusion)\n\n\n# Cloud Diffusion Experiment\nYou can check our GTC presentation on YouTube:\n[![](assets/front.jpg)](https://www.youtube.com/watch?v=L5h9kbMMzZs)\n\nSamples and training logs for the model generations can be found [here](https://wandb.me/gtc2023).\n\nThis codebase contains an implementation of a deep diffusion model applied to cloud images. It was developed as part of a research project exploring the potential of diffusion models for image generation and forecasting.\n\n## Setup\n\n1. Clone this repository and run `pip install -e .` or `pip install cloud_diffusion`\n2. Set up your WandB account by signing up at [wandb.ai](https://wandb.ai/site).\n3. Set up your WandB API key by running `wandb login` and following the prompts.\n\n## Usage\n\nTo train the model, run `python train.py`. You can play with the parameters on top of the file to change the model architecture, training parameters, etc.\n\nYou can also override the configuration parameters by passing them as command-line arguments, e.g.\n\n```bash\n\u003e python train.py --epochs=10 --batch_size=32\n```\n\n## Training a Simple Diffusion Model\n\nThis training is based on a Transformer based Unet (UViT), you can train the default model by running:\n\n```bash\n\u003e python train_uvit.py\n```\n\n## Running Inference\nIf you are only interested on using the trained models, you can run inference by running:\n\n```bash\n\u003e python inference.py  --future_frames 10 --num_random_experiments 2\n```\n\nThis will generate 10 future frames for 2 random experiments.\n\n## License\n\nThis code is released under the [MIT License](LICENSE).","funding_links":[],"categories":["Python"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftcapelle%2Fcloud_diffusion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftcapelle%2Fcloud_diffusion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftcapelle%2Fcloud_diffusion/lists"}