{"id":25640690,"url":"https://github.com/socketbyte/sdtoolkit","last_synced_at":"2025-04-15T02:50:59.299Z","repository":{"id":61122590,"uuid":"548486135","full_name":"SocketByte/SDToolkit","owner":"SocketByte","description":":robot: All in one, batteries-included software to easily generate and upscale AI art using Stable Diffusion","archived":false,"fork":false,"pushed_at":"2022-10-20T16:02:26.000Z","size":92,"stargazers_count":30,"open_issues_count":1,"forks_count":6,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-28T14:39:17.630Z","etag":null,"topics":["ai","art","generator","gfpgan","gpu","stable-diffusion","tools","upscaling","video2x"],"latest_commit_sha":null,"homepage":"","language":"C#","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/SocketByte.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}},"created_at":"2022-10-09T17:08:43.000Z","updated_at":"2024-09-02T07:05:59.000Z","dependencies_parsed_at":"2023-01-20T06:02:16.932Z","dependency_job_id":null,"html_url":"https://github.com/SocketByte/SDToolkit","commit_stats":null,"previous_names":[],"tags_count":6,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SocketByte%2FSDToolkit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SocketByte%2FSDToolkit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SocketByte%2FSDToolkit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SocketByte%2FSDToolkit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SocketByte","download_url":"https://codeload.github.com/SocketByte/SDToolkit/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248997087,"owners_count":21195797,"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":["ai","art","generator","gfpgan","gpu","stable-diffusion","tools","upscaling","video2x"],"created_at":"2025-02-23T04:46:22.533Z","updated_at":"2025-04-15T02:50:59.283Z","avatar_url":"https://github.com/SocketByte.png","language":"C#","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SDToolkit\n\nAll in one, batteries-included software to easily generate and upscale AI art using [Stable Diffusion](https://github.com/CompVis/stable-diffusion)\n\n\u003cdiv style=\"padding: 1rem; background-color: #ffad59; border-radius: 1rem; color: black; font-size: 1.15rem;\"\u003e\n    \u003cp style=\"padding: 0; margin: 0;\"\u003e\u003cb\u003eDisclaimer: \u003c/b\u003eThis software is still in beta, bugs can and will occur at some point. Please use the \u003ci\u003e\u003ca href=\"https://github.com/SocketByte/SDToolkit/issues\"\u003eIssues\u003c/a\u003e\u003c/i\u003e tab to report a bug. Thank you for using SDToolkit!\u003c/p\u003e\n\u003c/div\u003e\n\u003cbr/\u003e\n\n![img](https://i.imgur.com/5c2EjT5.png)\n![img](https://i.imgur.com/yXfs4YY.png)\n\n## Features\n\n- No setup required, just install and run\n- \u003ca href=\"https://github.com/k4yt3x/video2x\"\u003eVideo2x upscaler\u003c/a\u003e\n- \u003ca href=\"https://github.com/TencentARC/GFPGAN\"\u003eGFPGAN\u003c/a\u003e face restoration\n- Ability to choose a context image for AI to try to match\n- Result image viewer with zoom\n- Optimized for low VRAM GPUs\n- Many helpful tooltips that make it very easy to use\n- Decent amount of configuration options\n\n## GFPGAN Integration\n\nSDToolkit offers a built-in GFPGAN for face restoration. This is quite a powerful tool to remove face artifacts and beautify the result. It's definitely recommended to use GFPGAN for every prompt that might have faces in it.\n\n![img](https://i.imgur.com/UecbKYL.png)\n\n## Video2x Upscaler\n\nSDToolkit offers a built-in Video2x upscaler. Please remember that it isn't perfect, and upscaling by a very large factor can cause artifacts.\n\n![img](https://i.imgur.com/OQqkZW7.png)\n\n## Requirements / Info\n\n- OS: Windows 64-bit\n- At least 35GB of disk space\n- At least 8GB of GPU VRAM is recommended\n- At least 16GB of RAM is recommended\n- CUDA-enabled GPU is recommended (Nvidia)\n\nSince SDToolkit is all-in-one software, the model, upscaling software (video2x/GFPGAN) and execution environment (Conda/Python) is included in the setup.\n\nTested with i7-12700KF and GTX 1080 with full precision. (around 6.7GB of VRAM usage)\n\nHalf precision is recommended for RTX cards.\n\n## Installation\n\nJust download and run the setup from the Releases tab. Be reminded that it's a huge file, you should have at least 35GB of free disk space. Users running the v0.2-beta release, please refer to this \u003ca href=\"https://github.com/SocketByte/SDToolkit/releases/tag/v0.2-beta1\"\u003ehotfix\u003c/a\u003e for a comprehensive installation.\n\n## License\n\nThe software is licensed under GNU Affero Public License and the SD model is licensed under CreativeML Open RAIL-M. You're required to accept both to use this software. You're free to use the generated art files for commercial purposes as long as they conform to the license terms and conditions.\n\n## Used software/models\n\nThis software uses Stable Diffusion v1-4 model licensed under CreativeML Open RAIL-M.\nYou're free to download it yourself at [CompVis's huggingface repository](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original).\n\nScripts and model execution software provided by [basujindal's fork of stable diffusion](https://github.com/basujindal/stable-diffusion/).\n\nUpscaling model and algorithm is provided by [video2x](https://github.com/k4yt3x/video2x).\n\nGFPGAN 1.3 model and algorithm provided by [Tencent's GFPGAN](https://github.com/TencentARC/GFPGAN).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsocketbyte%2Fsdtoolkit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsocketbyte%2Fsdtoolkit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsocketbyte%2Fsdtoolkit/lists"}