
Just an intermediate REAL to CARTOON style enhancer/detailer.
Here are four LoRAs of different training levels. The difference is about one day of training per level. I suppose you can lower the strength of the MAX one and get something like the effect of the low level LoRAs, but I am not sure if it makes exactly the same thing.
The point of this LoRAs is to morph women’s shapes without changing the style completely, just adding some attractive. Experiment with the LoRA’s strength for desired effect. Don’t forget that the exact way each LoRA affects the image also depends heavily on that image /prompt content.
Experimenting with these LoRAs I found that they not only morph the style but also add more details, you can confirm this from the example images.
The whole work took me more than 2 weeks and if someone finds this cool I’ll be glad.
Likes and cross-posting of images in the gallery are welcomed if you get some decent content.
Good luck
描述:
The HIGH training level version for skilled prompt masters only, those who like to dance on the edge. Allows you to take full advantage of the potential of the LoRA, but if you suffer any kind of troubles with style consistency e.t.c., please, consider changing to the LOW or BEST versions.
训练词语:
名称: dreamgirl_high.safetensors
大小 (KB): 566853
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success