{"id":19223914,"url":"https://github.com/invoke-ai/invoke-training","last_synced_at":"2025-04-16T00:23:13.609Z","repository":{"id":185101477,"uuid":"672923821","full_name":"invoke-ai/invoke-training","owner":"invoke-ai","description":null,"archived":false,"fork":false,"pushed_at":"2024-06-09T16:35:30.000Z","size":61846,"stargazers_count":86,"open_issues_count":8,"forks_count":11,"subscribers_count":8,"default_branch":"main","last_synced_at":"2024-07-22T19:23:25.244Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://invoke-ai.github.io/invoke-training/","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/invoke-ai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"docs/contributing/development_environment.md","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":"2023-07-31T13:23:51.000Z","updated_at":"2024-07-21T20:18:01.000Z","dependencies_parsed_at":null,"dependency_job_id":"cb5d85de-068a-470f-87bd-a48b3e7de7cc","html_url":"https://github.com/invoke-ai/invoke-training","commit_stats":null,"previous_names":["invoke-ai/invoke-training"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/invoke-ai%2Finvoke-training","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/invoke-ai%2Finvoke-training/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/invoke-ai%2Finvoke-training/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/invoke-ai%2Finvoke-training/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/invoke-ai","download_url":"https://codeload.github.com/invoke-ai/invoke-training/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223842192,"owners_count":17212323,"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":"2024-11-09T15:09:53.047Z","updated_at":"2025-04-16T00:23:13.590Z","avatar_url":"https://github.com/invoke-ai.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# invoke-training\n\nA library for training custom Stable Diffusion models (fine-tuning, LoRA training, textual inversion, etc.) that can be used in [InvokeAI](https://github.com/invoke-ai/InvokeAI).\n\n\u003e [!WARNING] \u003e `invoke-training` is still under active development, and breaking changes are likely. Full backwards compatibility will not be guaranteed until v1.0.0.\n\u003e In the meantime, I recommend pinning to a specific commit hash.\n\n## Documentation\n\n\u003chttps://invoke-ai.github.io/invoke-training/\u003e\n\n## Training Modes\n\n- Stable Diffusion\n  - LoRA\n  - DreamBooth LoRA\n  - Textual Inversion\n- Stable Diffusion XL\n  - Full finetuning\n  - LoRA\n  - DreamBooth LoRA\n  - Textual Inversion\n  - LoRA and Textual Inversion\n\nMore training modes coming soon!\n\n## Installation\n\nSee the [Installation](https://invoke-ai.github.io/invoke-training/get-started/installation/) section of the documentation.\n\n## Quick Start\n\n`invoke-training` pipelines can be configured and launched from either the CLI or the GUI.\n\n### CLI\n\nRun training via the CLI with type-checked YAML configuration files for maximum control:\n\n```bash\ninvoke-train --cfg-file src/invoke_training/sample_configs/sdxl_textual_inversion_gnome_1x24gb.yaml\n```\n\n### GUI\n\nRun training via the GUI for a simpler starting point.\n\n```bash\ninvoke-train-ui\n\n# Or, you can optionally override the default host and port:\ninvoke-train-ui --host 0.0.0.0 --port 1234\n```\n\n## Features\n\nTraining progress can be monitored with [Tensorboard](https://www.tensorflow.org/tensorboard):\n![Screenshot of the Tensorboard UI showing validation images.](docs/images/tensorboard_val_images_screenshot.png)\n_Validation images in the Tensorboard UI._\n\nAll trained models are compatible with InvokeAI:\n\n![Screenshot of the InvokeAI UI with an example of a Yoda pokemon generated using a Pokemon LoRA model.](docs/images/invokeai_yoda_pokemon_lora.png)\n_Example image generated with the prompt \"A cute yoda pokemon creature.\" and a trained Pokemon LoRA._\n\n## Contributing\n\nContributors are welcome. For developer guidance, see the [Contributing](https://invoke-ai.github.io/invoke-training/contributing/development_environment/) section of the documentation.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finvoke-ai%2Finvoke-training","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Finvoke-ai%2Finvoke-training","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finvoke-ai%2Finvoke-training/lists"}