Mang Ning

+1

I've got the same problem on Colab. the model run at 20 fps on Tesla P100, but run at 0.5 fps by tflite. @theAIGuysCode could you please help us check...

hey guys @notou10 @zengxianyu @ader47 @LuChengTHU can you share which data source of FFHQ 256 you used as the reference batch to compute FID? I am thinking of using this...

Hi @unixpickle , thanks for the work and code. with the pre-trained model, I tested the conditional ADM-G and ADM on ImageNet64 with 100 sampling steps and dropout 0.1. **ADM...

Hi @sgbaird, did you figure out how to train an unconditional LDM? Is the undocumented readme file helpful?

for unconditional training and sampling, it is better to look at their [LDM repo](https://github.com/CompVis/latent-diffusion)

@simon-donike hi Simon, do you know the pre-trained model of FFHQ provides both diffusion and AE checkpoints when doing unconditional generation using script `sample_diffusion.py`?

> Releasing LVD-142M is not something that we are considering releasing, I am afraid. Re: open-sourcing the data curation code, this could depend on feedback and interest from the community....

`requirements.txt` has a compatibility issue now if I directly install by `pip install -r requirements.txt` the below versions work in my ubuntu 20.04: ``` numpy~=1.21.6 torch~=1.13.1 opencv-python~=4.7.0.68 scipy~=1.7.3 matplotlib~=3.5.3 cython~=0.29.33...

> Hi @Littleor I met a cuda-out-of-memory error after loading from a checkpoint before training. Do you have any idea why this happened? Training from scratch is ok. same here,...