It's another of my first attempts to train in SDXL. It's some kind of experiment, but I want to publish this one too as results are good enough. There is of course enough space to improvements, but getting in consideration that images generated are only with SDXL 1.0 without refiner, I am satisfied by now with generations.
LoRA weights should be between 1.1 and 1.4 in my experience.
For portraits you can use 896 x 1152, 832 x 1216, 768 x 1344, 640 x 1536 or even 768x1024 resolutions.
This LoRA has been trained after carefully selecting 22 images. All photos have been enhanced to make the most of them. I hope you like it!
I don't ask for anything but any respectful constructive review (after having tested the model) would be highly appreciated or at least press Like if you're happy with results after trying it out! Thanks in advance and enjoy it!
Notice: This free work is intended for art and illustration purposes of emergent technology and not intended nor' trained for making illicit images, as the author I've taken care to not use any private data in the training process or designed it for such purposes. By downloading this model you are agreeing with the aforementioned intent and that you will not use my work to create / share images of a potentially immoral and / or illegal nature.
Description
FAQ
Comments (4)
Much like the Ana de Armas lora, Dreamshaper overwhelms Gal's facial features.
I thought perhaps that this could be problem with the lora, but it looks like Dreamshaper needs to address it.
Anyway, you're not alone. Both of these loras are sub-100mb (as opposed to the massive 1+gig loras floating around). I don't know how the big ones fair in Dreamshaper.
Dreamshaper is in early phase by now. I am sure they will address it . In my case there is a lot to improve in near future. We are just beginning! Thanks for comments!!
Could you add another trigger keyword specific to this lora so we can combine your character loras together?
Something along the lines of galgadot.
I should have done before training in captions . But this will probably not be final version. I will think about it! Thanks for comments! ;)