Why is the loss of Diffusion model calculated between "RANDOM noise" and "model predicted noise"? Not between "Actual added noise" and "model predicted noise"?

🧨 Diffusers
4

I trained U-Net using the loss with “the actual added noise” that is, the noise added between “t-1” step and “t” step, NOT “random noise”.
then U-Net seems to be optimized faster.

Why we are using “random noise” for diffusion loss calculation and how this be possible?