Sign In

Mink (Dragon Half)

131

845

96

10

Updated: Dec 14, 2024

characteranimewoman

Verified:

SafeTensor

Type

LoRA

Stats

74

14

3

Reviews

Published

Dec 14, 2024

Base Model

SD 1.5

Training

Steps: 2,200
Epochs: 13

Usage Tips

Clip Skip: 2
Strength: 0.9

Trigger Words

mink
dragon_half
bikini armor
vambraces
detached sleeves
knee boots
dragon charm
dragon tail
dragon wings

Hash

AutoV2
818C9CDD4F
default creator card background decoration
4as's Avatar

4as

Mink is the main character from Dragon Half.

The main trigger for V3.0 is mink, with either dragon_half or dragon horns to specify a variant.

Default anime appearance: mink, dragon_half, bikini armor, detached sleeves, vambraces, dragon wings, dragon tail, knee boots, dragon charm.
Weight 0.9 - 1.0 is recommended.

Activation tags

1) mink is the main trigger. This won't add any horns, just Mink with her spiky hair and red eyes.
2) dragon_half or dragon horns. This might be a bit confusing, but to keep some compatibility with the previous versions dragon_half adds a standard pair of horns, like in the anime. While dragon horns is used to add 3 pairs of horns from her post-transformation manga appearance.
3) bikini armor, detached sleeves, vambraces, knee boots, dragon charm creates the outfit Mink is wearing in the anime. I spent a lot of time training each keyword separately, so you should be able to mix and match them, but some other concepts might bleed into the image from time to time.
4) dragon wings and dragon tail are self explanatory.

Bonus tags:
a) anime artstyle forces the anime aesthetics.
b) official art can be used to shift the art style toward the official illustrations.

Misc.

Versions 1.0 and 2.0 are obsolete and shouldn't be used.

Version 3.0 took a lot of time to make. I went over every image and manually edited them to unify the appearance, and create multiple variants for higher flexibility.

Trained on 215 images (x5 repeats), with person used as a class. 13 epochs, 32 DIM / 16 Alpha, Prodigy, 0.25/0.01/0.01 dropouts. Base model used for training was animefull_final, but the example images were created on AbyssOrangeMix.

Feedback is welcome.