What It Does
ControlNetApply combines three inputs: the existing conditioning (from CLIPTextEncode), a ControlNet model, and a reference image. The strength parameter controls how strongly the spatial guidance influences the output—higher values produce images that more closely follow the reference structure.
The reference image is a critical provenance gap: while the ControlNet model name and strength are recorded in the workflow JSON, the actual reference image content is not embedded in the output PNG. If the reference image is moved or deleted, that provenance link is broken.
Inputs
conditioningCONDITIONINGInput conditioning to modify.
control_netCONTROL_NETLoaded ControlNet model.
imageIMAGEReference image for spatial guidance.
strengthFLOATControlNet guidance strength (0.0–1.0).
Outputs
CONDITIONINGCONDITIONINGModified conditioning with ControlNet guidance.
What Numonic Captures
- ControlNet strength value
- Connection to ControlNet model node (traceable in workflow graph)
Known Gaps
- Reference image content — not embedded in output PNG
- Reference image file path — recorded but fragile (local paths)
- Preprocessor applied to reference image before ControlNet
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.