If you like the character, always leave a like and a picture, and if you give some buzz you will allow me to train other LORAs or MODELS. Downloading only is not useful. For model visibility, remember to rate the images in my gallery and leave a like. Thank you
Recommended Settings Version 4:
Lora: 0.9-1.0
CFG Scale 3.5-5.0
Steps: 24-50
Sampler: Euler a, Trained with AdamW8Bit
Engine: Kohya (Version 1-4)
Recommended Settings Version 5:
Lora: 0.9-1.0
CFG Scale 3.5-7.0
Steps: 24-50
Sampler: Euler a, Trained with AdamW8Bit
Engine: AIToolkit
Description
FAQ
Comments (2)
Hi! Sorry if I ask, but what changes in version 5 than version 4? I love your models. Cheers!
The differences between version 4 and 5 are, firstly, the minimally modified training file and, secondly, that this version was trained with AIToolkit (the previous ones with Kohya).