Michał Kaczmarek

Try to build it using docker. Works like charm after all env vars are set properely. I have tested it to use nvidia card using docker.

That's strange as mega-1 consumes 24GB on my RTX3090. I have built docker image and during build for dalle-backend I have a lot of info that it run out of...

@drdaxxy thank you for your explanation, I will try asap. That makes sense if JAX reserve most of possible resources. I should check docs for it.

Hi, also there is a hint if you have two different cards in the machine ;) Set `CUDA_VISIBLE_DEVICES=(number of card/s which are one type)` eg. `CUDA_VISIBLE_DEVICES=0` as I see JAX...

No image quality will not change - sometimes I have even worse results. 9 images query takes ~120-140s with 70ish% GPU load

 vs 

I assume that this issue is not related to quality of the model, so this should be moved to another topic. But in fact even dalle-mega image has issues with...