Joshua Lochner

Oh wow that's quite surprising! I have downloaded > 1 million transcripts for an ML project I'm working on (https://www.github.com/xenova/sponsorblock-ml) and only had 1 problem with this, so, it is...

Right, this is definitely a simple problem with an anything-but-simple solution. As you mentioned, the most important thing is not to break code that breaks modules which depend on it,...

Hi @churrodude666! Sorry for the late response, I've been busy with university for the past few months, but I have some time to work on this project now! :) I...

I took a look a younow and started implementing a basic scraper for chat: https://github.com/xenova/chat-downloader/tree/younow I am unsure how the chat normally runs (for some reason I was unable to...

Hi 👋 Yes, that is because it is in the development branch: https://github.com/xenova/chat-downloader/tree/younow and not yet in the live software. I was waiting for your response (and testing) before including...

Sure, I can fix that 👍 Do you have another example of a video I can test on?

Looks simple-enough to add. Will put it on the list (and hopefully implement it soon).

Well, I'm not too sure what you want me to do? If you need help reintegrating, you can ask a question and I'll try answer. Or, if you would like...

This sounds like an interesting idea. The thing is, you could make it using the python module. I spent 5 minutes implementing a basic version, which could look something like...

I believe it is because this implementation converts the output of the model back to images in the sampling function: https://github.com/lucidrains/denoising-diffusion-pytorch/blob/37334ae82467197ba3df194cae3a85332f5736be/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py#L535 So, to ensure that the final image is between...