guided-diffusion issues

How Can I use guided-diffusion at the denoising task?

I want to use the guided diffusion model not only in image creation but also in the de-noising task. So, starting with that experiment, I am trying to create clear...

SeunghyunKim1995

How can I get `classifier.pt` and `diffusion.pt` from `classifier_train.py`?

4

Hi, I'm Goo-Young Moon, a master's degree student at Korea University. I read your paper interestingly while investigating the research on diffusion models. But, I opened the issue as I...

gymoon10

Instability in 3D diffusion Model training

1

We are training a 3D diffusion model on medical data using this library and facing some instabilities during training. More in detail: The image quality stagnates/decreases after 80+ hours of...

simonasantamaria

How to put Image not noise as input of Gaussian Diffusiuon Network

1

I succeeded in learning guided diffusion using my custom data set. To check the performance of my neural network, I succeeded in generating a moderately noisy image through about 100...

SeunghyunKim1995

Inconsistent number of residual blocks per resolution level in downsampling vs. upsampling block

Hello, As the paper explains, the authors experimented with different numbers of residual blocks per resolution level. It is my understanding that the number should be identical for the downsampling...

tmartinezML

gradient of log classifing probability at \mu or at x_{t+1}?

1

Thanks very much for the source code. I find there is an inconsistency when calcaluating $p(x_t|x_{t+1},y)$: In paper, at the place after equation (6), gradient is $g=\nabla _ {x_t} \log...

JianjianSha