InvokeAI in one click.
InvokeAI is a stable diffusion studio with built-in model manager you can run on your own machine. Launch it in Even Stacks in one click, serve it over trusted HTTPS, and let your AI agents operate it.
What is InvokeAI?
InvokeAI is a Stable Diffusion implementation featuring a node-based canvas, workflow editor, and built-in model manager. It supports ControlNet, LoRA, and IP-Adapter and runs on most consumer NVIDIA, AMD, and Apple Silicon GPUs.
Run InvokeAI in Even
Even Stacks launches InvokeAI as a managed container on your own machine. No compose files, no manual setup.
- Open the Even Stacks panel in Even. The container engine starts on demand.
- Find InvokeAI in the one-click services and click Launch.
- Even pulls the image, starts it on port 9090, and serves it over trusted HTTPS at
https://invokeai.localhost.
Drive InvokeAI with your AI agents
Even ships an MCP, so any agent you run inside Even (Claude Code, Codex, and more) can operate InvokeAI directly, at both the UI level and the container level.
Through the Even MCP an agent can pull a model, call the local endpoint, and wire it into a tool, all on your own hardware. It runs commands inside the container, reads its logs, and for web apps opens and clicks through the interface in Even's own browser pane. Ask once, for example "set up InvokeAI and get it ready", and the agent handles it end to end.
More AI services
Other one-click services you can launch in Even Stacks.