ControlPartial Capture

Load ControlNet Model

class_type: ControlNetLoader

Source repo

Loads a ControlNet model that enables image-guided generation. ControlNets add spatial control (edges, depth, pose, segmentation) to the diffusion process, allowing precise composition from reference images.

What It Does

ControlNetLoader reads a ControlNet model file and prepares it for use with ControlNetApply. Different ControlNet models specialize in different guidance types: Canny (edge detection), Depth (depth maps), OpenPose (human poses), Scribble (rough sketches), and many others.

ControlNet usage is important provenance data because it fundamentally changes the generation process—the same prompt and seed will produce entirely different compositions depending on the ControlNet and reference image used.

Inputs

control_net_nameSTRING

ControlNet model filename.

Outputs

CONTROL_NETCONTROL_NET

The loaded ControlNet model.

What Numonic Captures

  • ControlNet model filename
  • ControlNet type (when detectable from filename)

Known Gaps

  • ControlNet model hash
  • ControlNet type when filename is ambiguous
  • Preprocessor settings used to prepare the reference image

Related Nodes

Capture ComfyUI metadata automatically

Numonic extracts workflow metadata from every ComfyUI generation — models, samplers, seeds, prompts, and custom nodes. Track provenance, maintain compliance, and never lose a workflow.