
Drunkoak - Artist Style ?
This Lora is trained on the super clean artworks of Drunkoak mostly known for his successful Pokemon videos on YouTube , if you're interested make sure to also check his work on Twitter or Pixiv .
Usage Tips :
-
regular use is at the weight of 1 to 0.9 , don't be afraid to experiment with higher values.
-
adding
drunkoak
to the prompt will give the LoRA a bit more influence over the shapes and composition of the image . -
This LoRA will try to make make shading and color super sharp and clean to flesh out the exact style, if you don't want that then use weight lower then 0.75.
-
This is a stylized LoRA by nature so using it withing it realistic checkpoint or tags, my yield uncharted results.
Known issues :
-
somehow this lora will try to pull off a Gardvoir hair cut or color scheme whenever it gets "green hair" in the prompt ?,
Samples Settings :
-
Checkpoints : anyhentai19, AOM3 A3
-
Steps : 24 to 30
-
Sampler: DPM++ 2M Karras
-
CFG : 7
Weight Array:
Consider posting ur creation, I love to what u make with it ?
描述:
训练词语:
名称: drunkoakStyle-24.safetensors
大小 (KB): 37001
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success