Get early access to build and test build, be able to try all epochs and test them by yourself on Patreon or contact me for support on Discord
To support me you can buy me a coffe at https://ko-fi.com/antonioriolo
Training settings:
42 images, 15 steps, 10 epochs, you find many epochs (with test images using plot xy script) on my Patreon while supporting me.
Recommended settings:
Make sure you are aware on the usage instructions of LORA
Sampler: DPM++ SDE Karras (Recommended for best quality, you may try other samplers)
CFG Scale : 5 to 9
LORA weight for txt2img: reccomended 0.3-0.8 (best 0.5)
Keys: wearing sexy maid dress
This model is very easy to use, just use the keyword and if necessary give to it a weight.
If you don't specify the color it will be black and white as the majority of the images of the training. but you can start your prompt with something like "a woman, (wearing sexy maid dress:1.2), red dress" to choice a particular color.
You might also want to try different weights for the lora, i used 0.5 and it worked great. with higher weight it may be more accurate in the dress but you risk to get artifacts in your images or wierd faces.
Enjoy!
