Enaic31 Artstyle LoRA
Use Cases
The LoRA is in itself very compatible with the most diverse model. However, it is most effective when used with Kenshi or AbyssOrangeMix2.
The LoRA itself was trained with the token: skistyle. I would suggest using the token with AbyssOrangeMix2, but not with Kenshi, since I got better results that way.
The models mentioned right now
AbyssOrangeMix2 from WarriorMama777
Kenshi Model from Luna
Strength
I would personally use these strength with the assosiated model:
Soft-Version:
0.6-0.85 for AbyssOrangeMix2
0.5-0.75 for Kenshi
Hard-Version:
0.4-0.6 for AbyssOrangeMix2
0.3-0.55 for Kenshi
Description
Stronger influence on style
FAQ
Comments (10)
Not gonna lie, I don't think I've ever needed to specify transsexual or hermaphrodite in my negative or positive prompts but you do you man
I still use my negative of the old days and they work and at these times it was mostly necesarry to use these tags aswell. I don't want to spread anything wrong, so if it bothers people I don't mind removing it
@Nerfgun3 I don't think is insulting to anybody, don't worry
@Nerfgun3 I dont think it bothers anybody buddy so dont worry, I think the issue is that in reality less than a percent of a percent of the world is trans or a hermaphrodite (saying your trans but not actually having trans gender surgery isnt trans as the trans community has fought to point out many times). So don't change anything but remember the issue wasnt anyone being offended its just more that its extra inconvenience to apply these terms to every generation of images when the terms dont really apply to anyone but a tiny, tiny minority.
A great solution would be to leave the trans prompts but dont enable them by default, make it so you have to prompt (trans) for a trans output and that would 100% fix the issue
Tried with several versions of Orangemix, cannot produce the sketching style as shown. Deleted it.
I added even more example images made with AbyssOrangeMix_nsfw with metadata. But if you want the best results you shouldnt use models based on AnythingV3, since it is overtrained. But thank you for your review, appreciate it.
@Nerfgun3 same result. Tried also with anything V3. cannot have the sketching and flat effect.
@decten76 Did you enable loras? That's about the only thing I can think of. Sorry you're having some issues
Would love a style training guide for LoRA in Auto1111. All I can find are guides for characters/faces. Sucks, because I have a 3090 to do it with.
please sakura-oriko lora
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.