The artist keeps control of colour in Blender because the pipeline passes colour information through several independent channels. Structure is handled separately by the ControlNet maps.
Depth and canny ControlNets carry geometry and outlines (depth-and-canny-controlnet-maps-from-input, multi-controlnet-stack-strength-tuning).
The redundancy is intentional. He says it is 'Never Enough we're working with AI': any single channel can be ignored or distorted by the model, so several are stacked.
If the model takes too much freedom with colours, as in his demo, the first lever to try is a lower denoise. That keeps the output closer to the input latent.
See also Blender to ComfyUI SDXL image-to-image render pipeline, Component-level color naming (true color accuracy).