使用ilvr_sample.py生成的图像很模糊，包含很多噪声

[Supzekun]

Hello, I have trained an unconditional DDPM model on my own dataset using the P2-weight codebase. The model produces clear images, however when using it for ilvr, the resulting images are blurry, what is the reason for this? Are there any hyperparameters I should adjust?