
Updated with Flux version.
Check the version info for tips and Workflow.
The Lora is trained on MidJourney Images that use my "Personalised Style" + Watercolor
What is new in v2:
-
Significantly increased the training dataset
-
Added support for a wider range of concepts
-
Removed most of the biases that were present in v1 (closed eyes everywhere for example)
-
Added 3 different intensity of the colors ( intense , deep, soft colors)
-
My personal style is changed a little bit , so the images are more "crisp and clear"
Works without the trigger words ArsMJStyle, Watercolor
Works great in the 0.2 - 1.5 range.
Start ~1.
As Watercolor is strong existing style and looks really nice as an abstract painting, you can go pretty high with the strength and still get a nice result.
I hope you will enjoy this LoRA as much as I did creating it!
描述:
This is the SD 1.5 Version of the same Watercolor model, with minimal changes to the training images and slightly different capture.
Works without the trigger words ArsMJStyle, Watercolor
Works great in the 0.4 - 1.5 range.
Recomend starting with 0.8
As Watercolor is strong existing style and looks really nice as an abstract painting, you can go pretty high with the strength and still get a nice result.
训练词语: ArsMJStyle, Watercolor
名称: ArsMJStyle_-_Watercolor.safetensors
大小 (KB): 36980
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success