4th Tail LoRa extract

LoRa extract of 4th tail model.

3 sizes, the bigger - the more accurate.

Original model comes with 1300+ artist styles, (examples) lots of anime characters (kemonomimi, gacha, touhous, vtubers, etc.) and some other features.

After LoRa compression some artist are fine, some are damped but still works, others barely recognizable. Same for character knowledge and style mixing. See grids below.

But who cares if you only want to use a small part that satisfies you directly on your favourite model?

For v0.4.0 new extraction algo (Lycoris extraction) have been used, it should have more strength. However, Forge if not compatible with it yet, use L (simple lora) for it.

Also consider using higher LoRa weight.

Works with PonyDiffusion finetunes/mixes including Autism.

Prompting:

by ARTISTNAME

by is mandatory, then quality tags, your prompt with full character name like on boorus. Check out 4th tail description for more.