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:
40 images, 15 steps, 12 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 0.4-0.7 (0.5-0.6 best results)
Keys: wearing outfit, back view
In my experience with this model, i saw very good images while starting the prompt with "a woman in a , lights, sitting on a couch" you can change it a bit to get what you want.
Trigger words are not always necessary, but most of the time SD will try to draw a outfit with ears, in that case try to give a bigger weight to "wearing outfit" and move it at the beginning of your prompt.
Also for the weight of the model, i advice 0.55, nice outfits that follows the model and no distortion in girl models.
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
