This model was trained on 564 screencaps from the Ranma anime. No tag necessary to trigger the model, but some specific characters can be called through their respective danbooru tags. Seems to prefer the male characters though...
Also, it's overtrained af, so you will need to lower the weight quite a bit (~0.65) to not get the close-up shots.
Please upload your own generations on here, so I can get more information on how the model is doing! ?
質問があれば、日本語でもどうぞ！
描述:
训练词语:
名称: ranma_style_v1.safetensors
大小 (KB): 147569
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
原文链接：https://1111down.com/921646.html，转载请注明出处
