Jiayan Teng
Jiayan Teng
I guess that you first upscale low-res image using SRGAN and then conduct image-to-image on it using MultiDiffusion? And when upscale, is MultiDiffusion recommended more or Mixture-of-Diffusers?
Thank you!
 And it seems that corresponding lines are here?
The first stage model can be any diffusion, and the second stage is the model trained by relay diffusion. For example, see section "Performance Reproduction" below.
CogVideoXDDIMSampler is equivalent to #7 compute x_t without "random noise". Just set std_dev_t=0, no randomness. It's just a different way of writing the same formula.
Thanks for your reminder, we have added the quick start instruction at the beginning of the readme.
We use python 3.11. Sorry for not specifying the specific python version. We will clarify in Readme.
> Hello, will the results with the diffuser be better than those with the SAT? Besides, I find that the generated video of rigid objects will have a nice view,...
1. You can just set train_iters = epochs * dataset_size 2. just set "load" to the pre-finetuned model's directory path.
Setting the random seed can only make the script run with the same result each time, but it cannot make the same result in multiple runs of the same script....