LoRA is generated entirely from anime images.
Should work well with any model.
Check samples for prompts :)
Leave a like, comment, review but first of all, ENJOY ;)
If you wish to support me in my work,
you can do that here: Ko-Fi.com/LittleJelly
Description
lowered file size
"quality over quantity screencaps" in dataset
better curated tags
fixed LoRA learning seed
FAQ
Comments (12)
Is Ru Rushi version 1 now not Lora? can you tell me
What do you mean? It's still available.
I just don't recommend using it, as it was trained with bad settings.
@LittleJelly Yes, it is true. In fact, it can be downloaded perfectly but stable diffusion doesn't know that what is being downloaded is Lora. and when I tried it in stable diffusion, it was not recognized by the machine. so that the diffusion results use the basic checkpoint model. can you check it? I beg u please.
@LittleJelly on stable diffusion i mean
@rtyuji works okay for me, sorry but you must be doing something wrong...
Anyways, I recommend you use v2 instead, it handles prompts much better.
@LittleJelly thank you then. Thank you again for responding so quickly. your work is really great. have a nice day
Can i use this model for sdxl 1.0 ?
The model is trained on SD1.5, so probably no.
@LittleJelly thanks then
Will you retrain this and the other isekai nonbiri loras on pony?
Thankfully they don't have more outfits, so I might do it sometime within the next 2 weeks.
@LittleJelly Thank you.