denoising-diffusion-pytorch

denoising-diffusion-pytorch copied to clipboard

teang1995

when do we use objective "pred_x_start"?

4

Hi diffusion developers, Thank you for the open source development! I have a naive question about the objective "pred_x_start". If we use this objective, after training we have a model...

liaocs2008

Greate repo! Could you please tell me how large the size of a 1D dataset should be ( have files with 250 time-steps)? In your paper it is stated that...

trs96

Hi @lucidrains , I wonder post-training, how we can load EMA weight of models for generation. Does `trainer.load()` automatically give you EMA weight? Thank you.

Leo-T-Zang

When should the model be saved, and how should it be implemented? I use torch.save(self.unet.state_dict(), f"{self.savepath}unet_checkpoint_{timestamp}_epoch_{epoch}.pth") and torch.save(self.diffusion.state_dict(), f"{self.savepath}diffusion_checkpoint_{timestamp}_epoch_{epoch}.pth") to separately store the weights of the unet and diffusion models....

ZH-UCAS

hi there, does this implemenation work for greyscale images dataset? and what changes would we need to do for using own greyscale dataset

awais00012

tran.py, test.py, and pre-trained weights

1

Hello, which .py file are the training and testing files? Also, aren't there pre-trained weights?

hhhhhh45

Generated images have pure blue/green parts

1

Hello, I basically gave an input image, add noise to t=100, and then sample it back to t=1. I got these generated images with pure blue/green parts. Any ideas why...

xuyingzhongguo

Can diffusion model be used into image to image translation ?

11

Can diffusion model be used into image to image translation ?

lianggaoquan

RuntimeError: No available kernel. Aborting execution.

7

I encountered an error while training the model. Specifically, during the save and sample process, the following error occurred: ``` pytorch/denoising_diffusion_pytorch/attend.py:77: UserWarning: Expected query, key and value to all be...

strmojo