This hypernetwork was trained on Anything-V3.0-pruned-fp32 [1a7df6b8] at a res of 512x768 and it's dataset included NSFW images. Additional checkpoints will be uploaded soon at various training steps. Edit: nvm apparently I won't be uploading additional checkpoints because the site won't let me (devs pls fix, thx). All of the versions were trained at their respective listed training steps and a learning rate of 0.00005. I personally like the results from v2-6000 the best.
Recommended keywords: portrait of midna, midna, 1girl, blue skin, forehead jewel, front ponytail, grey skin, orange hair, yellow sclera, pelvic curtain, hood, cloak, hooded cloak, hooded cape, cape, hood up, anklet, tattoo, leg tattoo, body writing, orange eyes, yellow eyes, purple lips, two-tone skin, neon trim
Recomended negative keywords: unibrow
Description
FAQ
Comments (3)
sorry but how can I add this to stable diffusion? There are tutorials explaining on how to create a hypernetwork but not how to add one from someone else
Just go to settings and select one (if you already copied file .pt into SD\models\hypernetworks)
looks amazing, but I can not use in my google colab :c, all the embeddings of 5 megas or more not work here, only the small embeddings of 1 mega or less maybe. Please do a light version :D