Mehdi Cherti

@afiaka87 thanks will definitely give a try to CLOOB, pre-trained models seem to be available (https://ml.jku.at/research/CLOOB/downloads/checkpoints/)

@pwaller just to be sure to understand, you computed CLIP text features of all words in `/usr/share/dict`, then did a nearest neighbour search of the word 'nebula' on the CLIP...

@pwaller I have trained some models using diversity loss like the one above but didn't make them available publicly yet. Here is a [link](https://drive.google.com/file/d/1vVlzIyNpOGpBmzga64v-1LNNsgQg0urF/view?usp=sharing) for the model above. You can...

@pwaller Happy to know you find it useful and have fun with it :) I have too. Sure, I just pushed a new branch https://github.com/mehdidc/feed_forward_vqgan_clip/tree/flow with support for normalizing flows...

Oh, actually I made a mistake, the branch is `net2net` https://github.com/mehdidc/feed_forward_vqgan_clip/tree/net2net

merged now into master, explanations in the README, where I refer to those as "priors"

So I guess similar answer here @CrossLee1, see issue #21. For the GPU it's A100s with 40GBs.

Hi @apolinario, thanks for your interest ! indeed the quality does not match the optimization approaches yet, the problem could come from the model architecture that is used and/or the...

Hi @zeke, sorry for my late answer, thanks for the proposition, you are absolutely right, the model names are not very informative. The thing is that the models are doing...

I would also be curious to see if training/fine-tuning CLIP on a higher resolution (e.g. 512x512 instead of 224) would also lead to better image quality for higher resolutions( >=...