trained on ID art starting from canto VI for NoobVpred1.0 + anima. there are many like it, but this one is mine

activation tag l1mp1p1

Anima Base

new cantos, 8-9-10

each picture had 2 prose captions: one without name "a single girl with blonde hair and yellow eyes..." and one with name "Don Quixote from Project Moon..."

It overcooked on QOH dress.

Anima v3 - mid + strong

trained on canto 8-9

Mid is more creative, better at facial expression, the pick for style mixing. Also more smudgy and anatomically erroneous.

Strong is stable and leans towards whiter lighting. Also rigid.

New face crops dataset from later cantos and uses came optimizer

Canto 8-9 version

51 epochs on id images from canto 8-9 and face crops from previous cantos.

Characters untagged; adding tags fucks up generalization. ABMOG optimizer really helped in making this. Adam and Prodigy refused to pick up the style - mayhaps skill issue.

Supposed to be shinier and fancier, but I'm not sure it is. Pruned a bit with lora resize tool to try and counteract repetitiveness. Can't quite say it helped, but didn't seem worse either.

-

• everyone have faust hair

• rigid

• grey, like half the dataset

+

• very awa

• i like it

If you want version with less epochs, tell me.