Pedro Cuenca
Pedro Cuenca
You are right, I'm late on this one! I'll work on an App Store release soon! 🚀
Yes, my apologies for the long wait! But the new release is very solid, thanks to @ZachNagengast we even have support for SD3!
Hi @svenkevs! In your original message, you mentioned the `split_einsum` version of the model, which is not available yet – only the `original` attention implementation has been converted. However, the...
Interesting, that was my mistake then! I'm not sure why it worked for me when I tested, but I'll fix it. Thanks @ZachNagengast!
I replaced the zip file in the repo with the correct version (I hope 😅). My apologies for the trouble! I'll open a new issue to prevent selection of the...
@beezbo There are two issues here: - The file structure of the palettized SDXL model was wrong. This is fixed. - The SDXL models are only available for GPU, but...
Hi @jgranie! Sorry, I'm not sure I follow. Would you like a warning when the prompt is too long and has to be truncated?
Hi @artofbeinghuman! Thanks a lot for your suggestion, I think it makes a lot of sense. Let's see if someone from the community gives it a go, otherwise we'll revisit...
Sorry @shanmugad, could you please clarify what you mean?
@rrva Yes, the split_einsum version is not ready yet. I have to make a fix to the app to never default to using it when it's not available (up until...