This has the same license as the 0.9 SDXL, so currently this is for research purposes!
Hello!
Since v1.0 is just around the corner, I would like to show you that training people LoRAs is very much possible.
Bear in mind, that those were tests so the quality might not be the best (also, the base is still v0.9, and v1.0 should be even better).
Samples might not be the best, I haven't used any refiners, just pure SD XL model and a LORA and nothing else.
The training dataset was of 1024x1024, so there was no upscaling (yes, freshly recut samples).
There will be still a lot of room for tweaks and improvements, you can compare it to the first dreambooths/loras. Still, as those were first tries - I'm positively surprised!
Here are three models that I was able to train during the beta. Enjoy!
I'm creating Dreambooths, LyCORIS, and LORAs. If you want to know how I do those, here is the guide: https://civarchive.com/articles/7/dreambooth-lycoris-lora-guide
I upload 2-3 times a week, however, I write down suggestions all the time. If you want to see someone made into a model just leave a comment :)
Suggestions left on my donation page ( https://www.buymeacoffee.com/malcolmrey ) are taken with the highest priority and you will be able to enjoy them way before they get released here. (I accept also custom requests)
The reason is that I can't keep up with uploading and the models are being made pretty much all the time :-)
As mentioned, via the donation page I accept custom requests, so feel free to engage with me there, I will answer all your questions :)
Description
Anna Kendrick SD XL