
I have created three model and this seems to give the best results from my experiments with different settings. I will update it in the future (next week maybe :D)
I recommend any of these resolution with hi res fix:
512x512
512X768
768x768
LoRa weights: 0.7-0.8 or you can experiment on your own to see what what gives the best result :D
描述:
训练词语: leo_tsukinaga,1boy
名称: leo_tsukinaga.safetensors
大小 (KB): 36976
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success