invoke-ai/InvokeAI

Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.

Invoke AI – Professional Creative Engine for Visual Media

What it is – Invoke AI is an open‑source application that lets you run state‑of‑the‑art text‑to‑image models (Stable Diffusion, Flux, CogView, Qwen‑Image, etc.) on your own hardware. It ships a local web server with a React UI, so you interact through a browser rather than the command line.

Key capabilities

  • Web UI & Unified Canvas – a polished, browser‑based interface that includes a drawing canvas, in‑/out‑painting brushes, and tools for refining AI‑generated pictures.
  • Workflow / Node system – build custom generation pipelines by connecting nodes (e.g., prompt → model → upscaler → post‑process) and save/share them.
  • Gallery & Board – automatically stores images with full metadata (prompt, seed, settings) and lets you drag‑drop pictures into any UI element for remixing.
  • Broad model support – ready‑to‑run checkpoints for SD 1.5, SD 2.0, SDXL, SD 3.5, Flux 1.x/2.x, CogView 4, Qwen Image, ERNIE‑Image, and many others, plus API‑only models like Nano Banana and GPT Image.
  • Extension ecosystem – supports ckpt, Diffusers, and some gguf formats; includes upscalers, an embedding manager, model manager, and segmentation tools (SAM/SAM2).

How to get started

  1. Download the Invoke Launcher from the linked GitHub releases page.
  2. Run the launcher; it will install the necessary Python/conda environment (or Docker, if you prefer) and pull any selected models.
  3. Open the local URL (usually http://localhost:9090) to access the UI.
  4. Use the Canvas to type a prompt, adjust settings, or paint masks, then hit Generate.

Typical users & use‑cases

  • Artists & designers who want a fast, locally‑hosted AI collaborator for concept art, storyboards, or texture creation.
  • Content creators needing batch generation, upscaling, or automated workflows for social‑media graphics.
  • Developers & researchers who can extend the node‑based workflow, plug in custom models, or integrate Invoke AI into larger pipelines.

Community & support

  • Active Discord community and detailed FAQ for installation problems.
  • Open contribution model – documentation, code, and feature requests are welcomed via GitHub.
  • Sponsorship options for individuals and businesses that want to fund ongoing development.

License – The core code is released under a commercially‑friendly open‑source license (the README notes “Free to use under a commercially‑friendly license”).

All information above is taken directly from the project's README.

Related

  • Project
    chatfire-AI/huobao-canvas

    Huobao Canvas is an open‑source, node‑based visual editor that lets you chain text, image, and video AI models from 11 providers on an infinite canvas. It offers a lightweight Node server for persistence and async run queues, Docker and Electron deployment options, and a single‑key setup via Huobao. Ideal for building multimodal creative pipelines without writing code.

  • Project
    basketikun/infinite-canvas

    An open-source AI image creation workbench that integrates an infinite canvas, multi-modal AI generation, and agentic canvas manipulation into a single workspace.

  • Project
    YanWenKun/ComfyUI-Windows-Portable

    A ready‑to‑run Windows package that bundles ComfyUI (a node‑based UI for Stable Diffusion) with 40+ custom nodes and 300+ pre‑compiled Python packages, letting users launch AI image/video generation instantly on an NVIDIA GPU.

  • Project
    Comfy-Org/comfy-cli

    comfy‑cli is a Python command‑line tool that installs, launches, and manages ComfyUI (an open‑source generative‑media engine). It handles environment setup, custom‑node installation, model downloads, workflow execution, and can offload jobs to the hosted Comfy Cloud service. Features include fast `uv`‑based dependency resolution, JSON‑structured output for LLM agents, shell completion, and utilities for testing PRs and managing background servers.

  • Project
    anymouschina/TapCanvas

    An Agent-native infinite canvas for AI film and multimodal content production that integrates scripts, storyboards, and assets into a traceable workflow.