Integrations / InvokeAI

RunDocumented

Run InvokeAI on a cloud GPU

Start the InvokeAI interface on a cloud GPU for image generation and editing, then stop it when you finish.

The steps follow the tool's documented settings. No tested run is recorded for this page yet.

Why use Badgr for InvokeAI

Badgr interface
Serve
Where InvokeAI fits
Application runtime
Why Badgr
AI image application hosting
  • Start InvokeAI on a cloud GPU for a session instead of keeping a machine.
  • Stopping it ends billing, and a cost cap bounds the session.
  • It is interactive and bills until stopped, which is stated up front so there are no surprises.

What you can do

  • Generate and edit images in the InvokeAI interface
  • Try larger models than your own GPU allows
  • Short creative sessions without a permanent server

Quickstart: Start InvokeAI

badgr serve template invokeai

How it works

  1. 1.You start the template
  2. 2.Badgr gives you an address
  3. 3.You open it and work in the interface
  4. 4.You stop it and billing ends

What you get

  • Images you download from the interface
  • A receipt when you stop it

Requirements

  • The Badgr CLI installed and logged in (npm install -g badgr-cli)
  • A funded Badgr balance
  • Model files or a model source you are allowed to use

What it costs

  • InvokeAI is interactive, so it bills for as long as it is running, even while idle.
  • Pass --max-cost and stop it with badgr down <id> when you finish. For work that ends by itself, use a finite job instead.

See pricing for how billing works.

Proof

No tested run is recorded for this integration yet. A receipt and example output will be added here after a real run, not before.

Troubleshooting

  • Bill keeps growing

    An interactive service runs until stopped. Run badgr status and badgr down <id>.

  • Models disappeared

    Files are removed when the service stops. Download what you need first.

  • Out of GPU memory

    Use a smaller model or lower the image size.

Developer reference

Ready to start with InvokeAI?

Every run or service has a spending limit you set before it starts.