Closed Manan006 closed 2 years ago
Hello! Thank you very much for your interest in the repo! A few weeks ago I tried to add multi-processing to do what you propose, but the bot was freezing during the inference, if you manage to do it I will gratefully accept the pull request, I've already added the hacktoberfest tag.
You can also try changing the model to keras, as it has recently been released https://keras.io/guides/keras_cv/generate_images_with_stable_diffusion/. But if you switch to keras I would prefer it to be in a new bot file like bot-keras.py and a requirement-keras.txt, as it is a major change.
Thank you and don't be afraid to ask for whatever you need! 😃
I'm not very knowlegde in machine learning yet so I won't be changing to keras but I'll do my best to make this into a truly async piece of code.
Also any plans to add support for https://github.com/basujindal/stable-diffusion
No problem, in the next few days I will create the keras implementation, so you will be able to try multiprocessing on both models, in case the current one doesn't allow you to do it because of freezing.
Thanks!
It is closed due to inactivity. Please reopen it if you have any progress.
So I think I could add some multiprocessing and allow the users to get response from the bot for multiple images at once. I wanna know if you're gonna be adding the hacktober tag to your repo, If you are then I'll be very happy to make a pull request with multiprocessing.