Jianyi Wang
Jianyi Wang
@aimerykong Thanks for your sharing. But currently, I cannot access to the zip00 file which needs right to access. Would you mind share the access to this file with me?...
@axmav Hi, axmav, have you successfully downloaded the dataset? How to download it? I met the same problem.
@nmichlo Hi, Nathan. Thanks for the awesome work. May I ask how to evaluate the metrics in this repo on MINST? Since there is no ground-truth, it is not possible...
> Hi there @IceClear, thank you for the kind words! > > Unfortunately it is not possible to calculate these metrics directly on MNIST, the dataset itself is not intended...
> > I want to use the mmgen module in my own project but I have been struggling with the installation. I couldn't find any issues on the topic. Any...
Hi, I also wonder why the code is different from the paper, especially for the missing of color jitter and box blur described in the journal version. Thanks a lot...
I guess the code currently does not support v-sampling: https://github.com/Stability-AI/stablediffusion/blob/main/ldm/models/diffusion/ddpm.py#L920
> Hi @danthe3rd Thanks for the very quick response! > > 1. Indeed, it is a training iteration including backward pass, optimizer step, etc. (see the linked `train.py` script with...
@YoelShoshan Hi, have you solved it? I also have similar issues. BTW, I just wonder will it be very difficult to support custom attn_bias? @danthe3rd Thanks in advance.
I guess the code currently does not support v-sampling: https://github.com/Stability-AI/stablediffusion/blob/main/ldm/models/diffusion/ddpm.py#L920