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 – Open‑source visual‑media generation platform

What it is

  • A locally‑run application that lets you generate, edit, and iterate on images with modern text‑to‑image models (Stable Diffusion, SDXL, Flux, etc.).
  • Provides a web‑based React UI and a unified canvas where you can paint, in‑/out‑paint, and apply brush tools while the AI acts as a creative collaborator.

Key capabilities

Feature What you can do
Web server & UI Launches a local web server; interact through a polished browser UI.
Unified Canvas Paint, mask, and modify images directly; supports in‑painting, out‑painting, and brush‑based refinements.
Workflows & Nodes Build node‑based generation pipelines (e.g., combine prompts, LoRAs, upscalers) and save/share them.
Gallery / Board Drag‑and‑drop images, view metadata (prompt, settings), and organise assets.
Model support Runs dozens of checkpoints and diffusion families: SD 1.5/2.0/XL, SD 3.5, Flux 1/2, CogView 4, various Qwen‑Image, ERNIE‑Image, Krea, etc.
Extensibility Handles .ckpt, Diffusers, and some GGUF formats; includes model manager, embedding manager, upscalers, and SAM/SAM2 segmentation tools.

Installation

  1. Download the official launcher from the Invoke AI Launcher releases page.
  2. Run the launcher; it will download required dependencies, set up a Python environment (or Docker if you prefer), and pull the selected model files.
  3. Open the local URL (usually http://localhost:9090) to start using the UI.

Typical workflow

  1. Choose a model (e.g., Flux.1 Schnell).
  2. Enter a text prompt or load an existing image on the canvas.
  3. Use brush tools to mask areas you want the model to modify.
  4. Run generation, tweak parameters, or chain nodes in a workflow.
  5. Save results to the gallery; reuse prompts or export images.

Who it’s for

  • Artists & designers who want AI‑assisted sketching, concept art, or rapid iteration.
  • Content creators needing batch generation or custom pipelines for marketing assets.
  • Developers & hobbyists looking for a self‑hosted, extensible alternative to cloud‑only services.

License & community

  • Released under a commercially‑friendly open‑source license (see NOTICE).
  • Active Discord community, regular releases, and a sponsor program that funds ongoing development.

Bottom line Invoke AI is a full‑featured, locally hosted creative engine for modern text‑to‑image models, offering a professional UI, canvas‑based editing, and node‑based workflow automation—all without needing a cloud subscription.

Related

  • Project
    basketikun/infinite-canvas

    An open-source visual workbench that integrates AI image generation, canvas orchestration, and prompt management into a single interface for continuous creative iteration.

  • Project
    tigerowo/infinite-canvas

    An open-source multimodal AI creative workbench that combines an infinite canvas with AI image, video, and audio generation tools to streamline visual iteration.

  • Project
    waooAI/waoowaoo

    An AI creative workspace for images and videos that combines an AI assistant, a visual canvas for organization, and integration with various generative models.

  • Project
    hero8152/Infinite-Canvas

    A visual, infinite canvas workspace that integrates multiple AI APIs and local ComfyUI workflows for collaborative generative AI content creation.

  • Project
    bytedance/flowgram.ai

    FlowGram is an open‑source visual workflow framework (bytedance/flowgram.ai) for building AI‑agent pipelines. It offers a web SDK and a native desktop app with drag‑and‑drop canvases, built‑in LLM, HTTP, and code nodes, scoped variables, form generation, debugging, and versioned publishing. Quick start via `npx @flowgram.ai/create-app@latest` and extensive docs at flowgram.ai.