Decided to split my base model into realistic and anime styles because trying to both will worsen the quality of both styles.
This model leans on anime to cgi styles.
Recommended Parameters
Sampler: DPM++2M Karras, DPM++ SDE Karras, Euler a, DDIM
Sampling Steps: 20-30
CFG: 7-10
Clip: 2
Negative Embeddings: bad_pictures
Description
Much better prompt following over the first version. The model can now "wink with one eye closed" and produces better image quality with just (worst quality, low quality:1.4) negative prompt.