The eeveelution family LoRA
Also include "sky forme shaymin", "absol"
In v3 version add "kirara (from inuyasha)", "teto (from ghibli-nausicaa)"
If you want to try "feral" type, use (quadruped feral) prompt, and set higher weight.
v1/v2: base on Yiffy-e18
v3-YiffyMix : base on YiffyMix v30
v3-FluffyRock : base on FluffyRock-e27-o12
This is a LoRA model, you will need new version Automatic's 1111 SD-WebUI or additional-networks extension
Use e621 tags, no underscore, Stop at CLIP layers=1
Best setting = [network strength:0.5~0.8]
Description
Demo images generated on YiffyMix2 + lora (network strength:0.72)
Stop at CLIP layers=1
FAQ
Comments (7)
Hey guys, did you know that in terms of-----
V2 is worse than V1 in feral
What does stop at CLIP layers = 1 mean?
In LoRA training has "clip_skip" setting.
Base on SD model use stop at CLIP layers = 1
Base on NAI (Novel AI leak) model use stop at CLIP layers = 2
You can find "CLIP_stop_at_last_layers" in Stable Diffusion A1111 Web/setting
※about "Novel AI leak" see rentry.co/sdg_FAQ
same question
What would be the settings if i wanted to use this in easy diffusion?
Right now most of the result while do produce pokemon like pictures they are all mangled abonimations:D
A flurry of human-pokemon hybrids? Better try this one out. Exactly my deal, that's for sure.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.