Integrations / ComfyUI

RunDocumented

Run ComfyUI workflows on demand

Run a ComfyUI workflow on a cloud GPU without setting up a server. Images and videos come back as files.

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

Why use Badgr for ComfyUI

Badgr interface
Run
Where ComfyUI fits
GPU runtime
Why Badgr
Image and video workflows
  • Run a saved workflow without owning or configuring a GPU server.
  • Ask for more GPU memory only when a video workflow needs it, using one flag.
  • Outputs come back as files, and billing stops when the run ends.

What you can do

  • Render images from a saved workflow without owning a GPU
  • Run video workflows that need more than 24 GB of GPU memory
  • Batch a workflow over many input images

Quickstart: Run a workflow

badgr comfyui run workflow.json --max-cost 5

How it works

  1. 1.You give Badgr a workflow file
  2. 2.It checks the workflow and picks a GPU with enough memory
  3. 3.ComfyUI runs the workflow
  4. 4.Output files come back and billing stops

What you get

  • Generated images or videos
  • Logs and a receipt

Requirements

  • The Badgr CLI installed and logged in (npm install -g badgr-cli)
  • A funded Badgr balance
  • A workflow exported as API-format JSON
  • Models the workflow uses, available to download (a models manifest)
  • Custom nodes compatible with the ComfyUI version Badgr runs

What it costs

  • A job is billed for the time it runs and stops billing when your command exits.
  • Pass --max-cost to set the most a job can spend. Badgr stops it if it reaches the cap.
  • Badgr shows the rate for the GPU it picked before it starts. This page does not quote a fixed price.
  • Larger video workflows need more GPU memory. Use --min-vram to ask for it, which can raise the hourly rate.

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

  • Missing models

    Pass a models manifest with --models so Badgr downloads what the workflow names.

  • Incompatible custom node

    Use --check-nodes to list nodes you rely on. Nodes not bundled in the pinned ComfyUI image may fail.

  • Out of GPU memory

    Add --min-vram (for example 48) to ask for a larger GPU.

  • Workflow fails to load

    Export the workflow in API format, not the regular save format.

Developer reference

Ready to start with ComfyUI?

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