Why the parameters of the generator(Stage_C) model need to calculate the gradient when training the control net？

[xhh12381]

In train_c_controlnet.py, why the parameters of the generator model need to calculate the gradient when training the control net, and only the parameters of the control net are set in the optimizer, I think this will extremely increase the consumption of VRAM, and I would like to know if setting generator.eval().requires_grad_(False) will not affect the control net training.

[Unified-Robots]

In my opinion, the training of the controlnet dependents on the parameters, as the controlnet injects the information into the stageC modules to control the contents of the generated images.