
Lora trained in re-create Ookami Uo's art style.
This one gets messed if you add monocrome/grayscale to negative prompt, so don't do it or add it in a low weight like (monocrome:.7)
I rlly like see your reviews and generations. They are helpful for fix and train better models. Share some hearts at the previews that you like and feel free to leave your comments or requests, but I can't promise anything xd.
Version 2: LoKr
With this one, I finished re-training all the DoRa's. Maybe this one could be good for comparison because it seems to work in a similar way as DoRa version. Let me know your thoughts.
Weight: .8 - 1
Version 1: DoRa
Another try, I don't know why this gets that behavior, no one previous Lora/Lycoris do that. They just get a brilliant colors, well anyway, just one more test before drop or keep with Doras.
Do not add grayscale or negative to your negative prompt
Weight: .8 - 1
描述:
训练词语:
名称: ookamiuo_style_pony6_v1-000018.safetensors
大小 (KB): 264939
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success