Bikupan style

Preliminary hypernetwork trained on 600 unique images (1 200 after mirror) with a focus on faces (portraits). Low res images were upscaled, all images were stretched to 512x512, tagging done by "WD1.4 tagger" automatic1111 extension.

Recommend negative tags: author name, signature.

Hypernetwork structure: 1, 2, 2, 1

No dropout, no normalization

LN and steps: 5e-6 first 13 000 steps (focus on faces), remaining 5 200 steps 1e-5 (variety of poses, multiple subjects, etc)