Question about the function p_losses in denoising-diffusion-pytorch :)

[BEbillionaireUSD]

Hey, thanks for the wonderful work!

Just a small question. I am wondering whether x = self.q_sample(x_start = x_start, t = t, noise = noise) is the corrupted img, in https://github.com/lucidrains/denoising-diffusion-pytorch/blob/main/denoising_diffusion_pytorch/denoising_diffusion_pytorch_1d.py Line 663, inside the p_losses function.

Looking forward to your reply.