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.
All images produced with AnythingV3 model + its VAE
Popularity
Info
Version V0.5: 1 File
About this version: V0.5
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)
2 Versions
Go ahead and upload yours!
