Apply ControlNet (Advanced)
Injects spatial structure from depth maps, OpenPose skeletons, or Canny edges across a chosen percentage window of sampling steps. Package: Built-in Core.
Updated Oct 17, 2026 · 1 min read
- Node / Pack
- Apply ControlNet (Advanced)
- Category
- conditioning
- Inputs
- positive, negative, control_net, image, strength, start_percent, end_percent
- Outputs
- positive (CONDITIONING), negative (CONDITIONING)
- Source Pack
- Built-in Core
What Apply ControlNet (Advanced) does in a ComfyUI graph
Injects spatial structure from depth maps, OpenPose skeletons, or Canny edges across a chosen percentage window of sampling steps.
On the canvas, this node accepts `positive, negative, control_net, image, strength, start_percent, end_percent` and emits `positive (CONDITIONING), negative (CONDITIONING)`. Every pin is color-coded by data type so you cannot accidentally wire a pixel `IMAGE` tensor into a `LATENT` pin without an intermediate encode step.
Installation and missing-node recovery on Windows
Apply ControlNet (Advanced) ships inside the default ComfyUI core on Windows. Double-click anywhere on the empty Studio canvas and type its name to drop it into your graph.
Download the full Windows desktop or portable package at /download to get started with a clean Python 3.12 environment.
FAQs
How do I fix "Apply ControlNet (Advanced)" showing up as a red box in ComfyUI?
Update your ComfyUI installation to the latest build from /download so all recent core nodes are registered.
What are the main inputs and outputs of Apply ControlNet (Advanced)?
Inputs: positive, negative, control_net, image, strength, start_percent, end_percent. Outputs: positive (CONDITIONING), negative (CONDITIONING).
Run on your hardware. Free forever.
The full ComfyUI engine: open source, fast, extensible, and yours to run however you want. Download the desktop app and open this workflow on your own machine.
