Hanusz Leszek

> This doesn't seem to work anymore. It generates an image then it disappears. I don't have access to my computer until tomorrow. I'll check it then. It should work...

@MrKuenning I just tested with the latest automatic1111 version and it works correctly for me, without modification. If you still have a problem, please report it on [my repo](https://github.com/leszekhanusz/diffusion-ui/issues), and...

Yes, but I want to access it programmatically, meaning I'd do another request and receive this info in a nice json form that could be exploited by a program, not...

I've looked into this a bit more and in fact this already exists! All the info is there in the `/config` path! This should definitely get a mention in the...

Usually single spaces do not add tokens because the space is inside a lot of tokens already. If you have a few more spaces, then it will take only one...

It took me a lot of time to notice that the mtime was not modified and I wanted to know why the Makefile was running the task multiple times. It...

I had the same problem, `torchvision==0.13.0` is not enough, you have to ensure that the `torch` version is in sync following this [version matrix](https://github.com/pytorch/vision#installation) This made it work: ```bash pip3...

Thanks for this pull request. It is very useful for me for a quick and dirty templating mechanism. This will replace the texts from files containing .template to the corresponding...

> You can also run Llama 65B (a bit slow but not terrible) on a CPU and with 128GB RAM with llama.cpp You don't need 128GB RAM, 65B runs on...

> Hah, well I find it funny :) Do you think it is over the top? A little bit, but well, you're the chief :laughing: , I'll do the modification.