{"id":16599938,"url":"https://github.com/dirmeier/diffusion-transformer","last_synced_at":"2026-06-06T00:31:26.276Z","repository":{"id":255541299,"uuid":"846556598","full_name":"dirmeier/diffusion-transformer","owner":"dirmeier","description":"A diffusion transformer implementation in Flax","archived":false,"fork":false,"pushed_at":"2025-08-21T19:09:39.000Z","size":215,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-04-17T00:27:12.854Z","etag":null,"topics":["diffusion-transformer","dit","flax","jax","python"],"latest_commit_sha":null,"homepage":"","language":"Python","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/dirmeier.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"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":"2024-08-23T13:09:58.000Z","updated_at":"2025-08-21T19:04:51.000Z","dependencies_parsed_at":"2024-09-06T01:07:53.847Z","dependency_job_id":"322f0e88-fc0b-45f2-a5e2-6d608bcff424","html_url":"https://github.com/dirmeier/diffusion-transformer","commit_stats":null,"previous_names":["dirmeier/diffusion-transformer"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/dirmeier/diffusion-transformer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dirmeier%2Fdiffusion-transformer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dirmeier%2Fdiffusion-transformer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dirmeier%2Fdiffusion-transformer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dirmeier%2Fdiffusion-transformer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dirmeier","download_url":"https://codeload.github.com/dirmeier/diffusion-transformer/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dirmeier%2Fdiffusion-transformer/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33965591,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-05T02:00:06.157Z","response_time":120,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["diffusion-transformer","dit","flax","jax","python"],"created_at":"2024-10-12T00:13:02.461Z","updated_at":"2026-06-06T00:31:26.266Z","avatar_url":"https://github.com/dirmeier.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DiT\n\n[![ci](https://github.com/dirmeier/diffusion-transformer/actions/workflows/ci.yaml/badge.svg)](https://github.com/dirmeier/diffusion-transformer/actions/workflows/ci.yaml)\n\n## About\n\nThis repository implements the diffusion transformer (DiT) architecture\nwhich has been proposed in [Scalable Diffusion Models with Transformers](https://arxiv.org/abs/2212.09748)\nin Flax. We test the architecture using the EDM parameterization introduced in [Elucidating the Design Space of Diffusion-Based Generative Models](https://arxiv.org/abs/2206.00364).\n\n\u003e [!NOTE]\n\u003e The architecture does not follow the [original implementation](https://github.com/facebookresearch/DiT) exactly.\n\u003e For instance, we don't use label conditioning and just use a learnable positional encoding for the patches.\n\u003e The rest is fairly similar.\n\n## Example usage\n\nThe `experiments` folder contains a use case that trains an EDM (diffusion model) on MNIST-SDF.\nFirst download the latest release and install all dependencies via:\n\n```bash\nwget -qO- https://github.com/dirmeier/diffusion-transformer/archive/refs/tags/\u003cTAG\u003e\u003e.tar.gz | tar zxvf -\nuv sync --all-groups\n```\n\nTo train the model, just execute:\n\n```bash\ncd experiments/mnist_sdf\npython main.py\n  --config=config.py\n  --workdir=\u003cdir\u003e\n  (--usewand)\n```\n\nBelow are some samples drawn from the EDM using a DiT-B after training 100 epochs.\nIn my experiments, the UNet still works better, but that might just be how the hyperparameters have been chosen.\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"experiments/mnist_sdf/figures/sampled-images.png\" width=\"700\"\u003e\n\u003c/div\u003e\n\n## Installation\n\nTo install the latest GitHub \u003cRELEASE\u003e, just call the following on the command line:\n\n```bash\npip install git+https://github.com/dirmeier/diffusion-transformer@\u003cTAG\u003e\n```\n\n## Author\n\nSimon Dirmeier \u003ca href=\"mailto:simd23@pm.me\"\u003esimd23 @ pm dot me\u003c/a\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdirmeier%2Fdiffusion-transformer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdirmeier%2Fdiffusion-transformer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdirmeier%2Fdiffusion-transformer/lists"}