Qi Sun

https://drive.google.com/drive/folders/1do_kCc5rNcPtSjeuQ_GF3BlEG-Zvtp86?usp=sharing

> if training prompts are better then cn wont learn to change style of sd because the style is already given in training prompts Can I solve this issue by...

> Looks like it's the problem of ffmpeg. Try to install ffmpeg from https://ffmpeg.org/download.html instead of conda. I used to meet some codec problems with ffmpeg from conda, and solved...

\> 24G is all you need (e.g. RTX 3090, V100)

## Local implementation I got such dependecies: torch==1.12.1+cu113 and corresponding torchvision and torchaudio packages.(nvcc --version->11.3 in my case) Then executing the following codes ``` $ git clone --recursive https://github.com/nvlabs/tiny-cuda-nn $...

what is the difference between lat and lat32?

> what is the difference between lat and lat32? Got it! latent is 64 dim. And we should train 2 autoencoder with different latent dimensions.