ComfyUI

Generate images with ControlNet guidance

Run a ComfyUI workflow that uses ControlNet (pose, depth, canny, or lineart) to constrain generation to a reference structure while a prompt drives style and content.

Run this jobGet help running this

Estimated $0.10–$0.40 per batch of 4 images · 1–3 min

What inputs you need

  • Reference image (pose/depth/edge map)
  • ControlNet model + conditioning strength
  • Text prompt
  • ComfyUI workflow JSON

What Badgr returns

  • Generated image(s) matching the control structure
  • Preprocessed control map used
  • Run log

Recommended GPU routes

L40S 48GBA40 48GBRTX 5090 32GB

Estimated cost: $0.10–$0.40 per batch of 4 images · Estimated runtime: 1–3 min

Example command

badgr run "comfyui --workflow controlnet_pose.json --input pose.png" \
  --gpu L40S \
  --max-cost 3

Common setup failures Badgr avoids

Out-of-VRAM stacking multiple ControlNet models — Badgr routes multi-ControlNet workflows to 48GB-class GPUs.

Control map preprocessing mismatch with the ControlNet model version — the preprocessor is pinned per workflow at startup.

Ready to run this?

Launch from the dashboard, CLI, or Compute API. Max-cost protection included.

Run this jobBack to ComfyUI