{"id":15038792,"url":"https://github.com/acly/krita-ai-diffusion","last_synced_at":"2026-02-21T22:17:32.622Z","repository":{"id":192148915,"uuid":"686161611","full_name":"Acly/krita-ai-diffusion","owner":"Acly","description":"Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.","archived":false,"fork":false,"pushed_at":"2025-04-22T10:28:32.000Z","size":30608,"stargazers_count":8415,"open_issues_count":100,"forks_count":439,"subscribers_count":73,"default_branch":"main","last_synced_at":"2025-04-23T17:09:33.475Z","etag":null,"topics":["generative-ai","krita-plugin","stable-diffusion"],"latest_commit_sha":null,"homepage":"https://www.interstice.cloud","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Acly.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":".github/FUNDING.yml","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,"zenodo":null},"funding":{"github":"Acly"}},"created_at":"2023-09-01T22:52:13.000Z","updated_at":"2025-04-23T11:06:37.000Z","dependencies_parsed_at":"2023-12-19T15:09:18.712Z","dependency_job_id":"e593fbc7-70f9-422c-91fd-59bbe2e364a0","html_url":"https://github.com/Acly/krita-ai-diffusion","commit_stats":null,"previous_names":["acly/krita-ai-diffusion"],"tags_count":53,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Acly%2Fkrita-ai-diffusion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Acly%2Fkrita-ai-diffusion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Acly%2Fkrita-ai-diffusion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Acly%2Fkrita-ai-diffusion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Acly","download_url":"https://codeload.github.com/Acly/krita-ai-diffusion/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250477812,"owners_count":21437049,"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":["generative-ai","krita-plugin","stable-diffusion"],"created_at":"2024-09-24T20:40:15.167Z","updated_at":"2026-02-21T22:17:32.613Z","avatar_url":"https://github.com/Acly.png","language":"Python","readme":"\u003ch1\u003e\u003cimg width=\"64px\" src=\"ai_diffusion/icons/logo-128.png\"\u003e Generative AI \u003ci\u003efor Krita\u003c/i\u003e\u003c/h1\u003e\n\n✨[Features](#features) | ⭳ [Download](https://github.com/Acly/krita-ai-diffusion/releases/latest) | 🛠️[Installation](https://docs.interstice.cloud/installation) | 🎞️ [Video](https://youtu.be/Ly6USRwTHe0) | 🖼️[Gallery](#gallery) | 📖[User Guide](https://docs.interstice.cloud) | 💬[Discussion](https://github.com/Acly/krita-ai-diffusion/discussions) | 🗣️[Discord](https://discord.gg/pWyzHfHHhU)\n\nThis is a plugin to use generative AI in image painting and editing workflows\nfrom within Krita. Visit\n[**www.interstice.cloud**](https://www.interstice.cloud) for an introduction. Learn how to install and use it on [**docs.interstice.cloud**](https://docs.interstice.cloud).\n\nThe main goals of this project are:\n* **Precision and Control.** Creating entire images from text can be unpredictable.\n  To get the result you envision, you can restrict generation to selections,\n  refine existing content with a variable degree of strength, focus text on image\n  regions, and guide generation with reference images, sketches, line art,\n  depth maps, and more.\n* **Workflow Integration.** Most image generation tools focus heavily on AI parameters.\n  This project aims to be an unobtrusive tool that integrates and synergizes\n  with image editing workflows in Krita. Draw, paint, edit and generate seamlessly without worrying about resolution and technical details.\n* **Local, Open, Free.** We are committed to open source models. Customize presets, bring your\n  own models, and run everything local on your hardware. Cloud generation is also available\n  to get started quickly without heavy investment.  \n\n[![Watch video demo](media/screenshot-video-preview.webp)](https://youtu.be/Ly6USRwTHe0 \"Watch video demo\")\n\n## \u003ca name=\"features\"\u003e\u003c/a\u003e Features\n\n* **Inpainting**: Use selections for generative fill, expand, to add or remove objects\n* **Live Painting**: Let AI interpret your canvas in real time for immediate feedback. [Watch Video](https://youtu.be/AF2VyqSApjA?si=Ve5uQJWcNOATtABU)\n* **Upscaling**: Upscale and enrich images to 4k, 8k and beyond without running out of memory.\n* **Diffusion Models**: Supports Stable Diffusion 1.5, XL, Illustrious and Flux models\n* **Edit Models**: Supports Flux Kontext for instruction-based image editing\n* **ControlNet**: Scribble, Line art, Canny edge, Pose, Depth, Normals, Segmentation, +more\n* **IP-Adapter**: Reference images, Style and composition transfer, Face swap\n* **Regions**: Assign individual text descriptions to image areas defined by layers.\n* **Job Queue**: Queue and cancel generation jobs while working on your image.\n* **History**: Preview results and browse previous generations and prompts at any time.\n* **Strong Defaults**: Versatile default style presets allow for a streamlined UI.\n* **Customization**: Create your own presets - custom checkpoints, LoRA, samplers and more.\n\n## \u003ca name=\"installation\"\u003e\u003c/a\u003e Getting Started\n\nSee the [Plugin Installation Guide](https://docs.interstice.cloud/installation) for instructions.\n\nA concise (more technical) version is below:\n\n### Operating System\n\nWindows, Linux, MacOS\n\n#### Hardware support\n\nTo run locally a powerful graphics card with at least 6 GB VRAM (NVIDIA) is\nrecommended. Otherwise generating images will take very long or may fail due to\ninsufficient memory!\n\n\u003ctable\u003e\n\u003ctr\u003e\u003ctd\u003eNVIDIA GPU\u003c/td\u003e\u003ctd\u003esupported via CUDA (Windows/Linux)\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eAMD GPU\u003c/td\u003e\u003ctd\u003esupported but requires custom ComfyUI setup\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eApple Silicon\u003c/td\u003e\u003ctd\u003ecommunity support, MPS on macOS 14+\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eCPU\u003c/td\u003e\u003ctd\u003esupported, but very slow\u003c/td\u003e\u003c/tr\u003e\n\u003ctr\u003e\u003ctd\u003eXPU\u003c/td\u003e\u003ctd\u003esupported, may see performance issues (Windows/Linux)\u003c/td\u003e\u003c/tr\u003e\n\u003c/table\u003e\n\n\n### Installation\n\n1. If you haven't yet, go and install [Krita](https://krita.org/)! _Required version: 5.2.0 or newer_\n1. [Download the plugin](https://github.com/Acly/krita-ai-diffusion/releases/latest).\n2. Start Krita and install the plugin via Tools ▸ Scripts ▸ Import Python Plugin from File...\n    * Point it to the ZIP archive you downloaded in the previous step.\n    * ⚠ _This will delete any previous install of the plugin._ If you are updating from 1.14 or older please read [updating to a new version](https://docs.interstice.cloud/common-issues#update-plugin).\n    * Check [Krita's official documentation](https://docs.krita.org/en/user_manual/python_scripting/install_custom_python_plugin.html) for more options.\n3. Restart Krita and create a new document or open an existing image.\n4. To show the plugin docker: Settings ‣ Dockers ‣ AI Image Generation.\n5. In the plugin docker, click \"Configure\" to start local server installation or connect.\n\n\u003e [!NOTE]\n\u003e If you encounter problems please check the [FAQ / list of common issues](https://docs.interstice.cloud/common-issues) for solutions.\n\u003e\n\u003e Reach out via [discussions](https://github.com/Acly/krita-ai-diffusion/discussions), our [Discord](https://discord.gg/pWyzHfHHhU), or report [an issue here](https://github.com/Acly/krita-ai-diffusion/issues). Please note that official Krita channels are **not** the right place to seek help with\n\u003e issues related to this extension!\n\n### _Optional:_ Custom ComfyUI Server\n\nThe plugin uses [ComfyUI](https://github.com/comfyanonymous/ComfyUI) as backend.\nAs an alternative to the automatic installation, you can install it manually or\nuse an existing installation. If the server is already running locally before\nstarting Krita, the plugin will automatically try to connect. Using a remote\nserver is also possible this way.\n\nPlease check the list of [required extensions and models](https://docs.interstice.cloud/comfyui-setup) to make sure your installation is compatible.\n\n### _Optional:_ Object selection tools (Segmentation)\n\nIf you're looking for a way to easily select objects in the image, there is a [separate plugin](https://github.com/Acly/krita-ai-tools) which adds AI segmentation tools.\n\n\n## Contributing\n\nContributions are very welcome! Check the [contributing guide](CONTRIBUTING.md) to get started.\n\n## \u003ca name=\"gallery\"\u003e\u003c/a\u003e Gallery\n\n_Live painting with regions (Click for video)_\n[![Watch video demo](media/screenshot-regions.png)](https://youtu.be/PPxOE9YH57E \"Watch video demo\")\n\n_Inpainting on a photo using a realistic model_\n\u003cimg src=\"media/screenshot-2.png\"\u003e\n\n_Reworking and adding content to an AI generated image_\n\u003cimg src=\"media/screenshot-1.png\"\u003e\n\n_Adding detail and iteratively refining small parts of the image_\n\u003cimg src=\"media/screenshot-3.png\"\u003e\n\n_Modifying the pose vector layer to control character stances (Click for video)_\n[![Watch video demo](media/screenshot-5.png)](https://youtu.be/-QDPEcVmdLI \"Watch video demo\")\n\n_Control layers: Scribble, Line art, Depth map, Pose_\n![Scribble control layer](media/control-scribble-screen.png)\n![Line art control layer](media/control-line-screen.png)\n![Depth map control layer](media/control-depth-screen.png)\n![Pose control layer](media/control-pose-screen.png)\n\n## Technology\n\n* Image generation: [Stable Diffusion](https://github.com/Stability-AI/generative-models), [Flux](https://blackforestlabs.ai/)\n* Diffusion backend: [ComfyUI](https://github.com/comfyanonymous/ComfyUI)\n* Inpainting: [ControlNet](https://github.com/lllyasviel/ControlNet), [IP-Adapter](https://github.com/tencent-ailab/IP-Adapter)","funding_links":["https://github.com/sponsors/Acly"],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Facly%2Fkrita-ai-diffusion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Facly%2Fkrita-ai-diffusion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Facly%2Fkrita-ai-diffusion/lists"}