Zhiwei ZHANG

Hi, thanks for your significant work. Could you give any suggestion on model training, such as epoch, number of GPUs? Before that, I trained DDPM on CIFAR10 with 800k iterations...

A new sampler for your reference

1

https://github.com/zzw-zwzhang/Yoneed/blob/main/sampler.py#L15

A proposed two-step GAN compression for anomaly detection. The performance of distillated student GAN can exceed teacher GAN. If possible, you can try it on the task of image synthesis....

more experimental results

Could you provide the evaluation code ? Thank you.

Thanks for your interesting work. How about the model size of LDM, compared with StyleGAN and ProjectedGAN?

Could not reproduce the results on CIFAR-10

8

I used your provided model-790000.ckpt on DDIM codebase to generate cifar10 images. But I got the FID is **4.818.** Is there any difference?

Hi, I am reproducing your work, could you please update the code and fix the error? thanks

Traceback (most recent call last): File "/home/a/anaconda3/envs/diffusion/lib/python3.8/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/home/a/anaconda3/envs/diffusion/lib/python3.8/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "main.py", line 45, in setup fn(config) File "main.py", line...