Hello welcome!
Here I leave a small introduction of the LoRA:
This week I was organizing my models, uploading most of them to pixai and adding others to Tensor...
Well, I think if I hadn't done this I would have created more repeat prompts XD
and that's it, this one here is one of the last ones I had saved and I didn't remember until now, it's number 30 of the normal ones :3
Description
FAQ
Comments (3)
This LoRA is really good at providing white and simple backgrounds for the generations, but it gets quite overwhelming and loses quality when used above <0.5 in my case.
Anyone else experience the same thing? Really loving the previews, and would love to master it.
Does OP have any tips on how to properly set it up?
Hello, I'm sorry to reply now (I thought I had already done so when I liked it...)
I usually use it as AD in tensor so as not to lose quality in the faces, I also just uploaded it to pixai. Although I have always used it from 0.7 onwards, I recommend using Hassaku as a Base model, you can also copy the general tag of any booru (you will be surprised) or add 1boy, 1girl, etc... when you want collages not to be generated, that only happens to me when I do not use character lora.
here are some examples:
https://pixai.art/model/1694709893834550236
Here are some examples that I just made, I used 0.7 as lora and inAD I used 0.8:
@Herrscher_AGGA2023 Thanks for the explanation and sharing the links! Will give it a look!
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.