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:
33 images, 20 steps, 13 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 0.4-0.8 (0.6-0.7 best results)
Keys: wearing ???? sailor outfit, on a boat, back view
This model is very easy to use, just start your prompt with something like "a woman, wearing ???? sailor outfit" might be necessary to give a weight to the keyword, i used 1.3 in my prompts because with less weight the image generated was usually with a ??????. So start your prompt like "a woman, (wearing ???? sailor outfit:1.3)"
I didn't manage to draw good hands using this model, might be necessary to inpaint to fix hands.
The model is training on different color outfits, this mean you can decide wich color will be the outfit by adding in your prompt stuff like "blue outfit" or "red outfit" or "pink outfit" etc...
The images posted are all realistic images on a boat, but you can generate images everywhere you want, just don't use the keyword "on a boat". You can also generate anime and ?????? using this model with a proper prompt and a proper checkpoint.
Enjoy!
If you'd like to support my efforts and have access to early and bleeding edge builds, please think about joining my Patreon: https://www.patreon.com/betterCuteAsians
