5th tail

This is my finetune of Animagine XL v3

Basically same dataset as for previous version of 4th tail used, but with new improved training technique and some tuning.

New approach allows to achieve great style knowledge - more then 110 (actually over 200) embedded artist styles! List can be found [here], it can be used directly as a wildcard.

No need to collect a bunch of LoRAs with questionable quality, just use prompt like with NAI3 and some other models.

• Good knowledge of many characters by simple prompt is the merit of the Animagine3, so just some polishing for fox-,cat-,wolf-,... girls, as well as some popular characters from gacha games.

• Speaking about kemonomimi - original model sometimes lacks tails accuracy, 5th tail aims to solve this issue, check out the examples.

• For some pictures in dataset hybrid captioning (combination of booru tags + natural language) was used, so model has good natural prompting capabilities, use it for best results.

• As one of the main goal added bonus - boost in NSFW. It does not performs as well as PonyDiffusion (check out my 4th tail model) but can generate E rating pictures with cute girls in front of detailed and coherent backgrounds.

Prompting is simple

put

by _ARTISTNAME_

first if needed, then use booru tags and natural text as you desire. Finish with quality tags.

Tweaker tags can be applied:

hdr, sdr, soft_background, sharp, high_contrast, low_contrast, limited_range

All works as expected, can be placed both in positive and negative prompts with corresponding effect. Note that underline _ is mandatory!

By the way, model is not lobotomized and works perfectly fine with any character, regardless of tail and animal ears presence.

Full compatibility with Animagine XL v3 LoRAs.

Known issues (to be fixed in new versions):

• Suzuran (and possibly some other chars) does not like to changes outfits. Negatives for original costume helps.

• Some combinations of artists styles (3+) works too aggressively. Can be solved by lowering weights or using [a | b | c] to alternate promb between sampling steps.

License: Same as for Animagine XL V3 Fair AI Public License 1.0-SD

New versions soon!

Special thanks to my fellow brothers who share the same cultural beliefs and helped to make it real.