ddim
ddim copied to clipboard
ermongroup
Denoising Diffusion Implicit Models
Thanks for sharing the code! While I get the following error when I run the demo code of the diffusers. ``` diffusers/src/diffusers/schedulers/scheduling_ddpm.py line 258 got an unexpected keyword argument `eta`...
I don't understand why use it. ```python class Downsample(nn.Module): def __init__(self, in_channels, with_conv): super().__init__() self.with_conv = with_conv if self.with_conv: # no asymmetric padding in torch conv, must do it ourselves...
I want to calculate the FID for CelebA or LSUN datasets by writing the code: `fidelity --isc --fid --input1 ./logs/cifar10_generated --input2 cifar10-train` (Code example is CIFAR-10). But I don't know...
Hi, It's a work with great impact. And I had a problem to understand the formula in eq52 (Accelerate sampling). May I wondering that: 1. why eq52 have a additional...
In the diffusion.py file, during uniform sampling, the sequence is obtained as follows: skip = self.num_timesteps // self.args.timesteps seq = range(0, self.num_timesteps, skip) However, when sampling 10 steps, the generated...
According to https://github.com/pytorch/pytorch/pull/97863 torch._six has been removed. I propose the following modification to avoid the error "module 'torch' has no attribute '_six'". This solution is also suggested in other projects:...
