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
描述:
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.
训练词语:
名称: versamixAnime_v20.safetensors
大小 (KB): 2082642
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
