https://civitai.com/models/181857?modelVersionId=439463
V3.0 verson
更好的还原度，更好的人体，更温馨的画风
better restoration, better human figures, and a warmer art style.
Training model: Animagine XL V3.1
Inference model: Animagine XL V3.1
Training resolution: 10241024
Recommended output resolution: 10241280 /832*1216
Recommended model weight: 0.8~1
