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

Training settings:

35 images, 25 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 0.4-0.7

• Keys: wearing ballet dress, wearing tutu, in theater, in a studio, ballet pose (doesn't always work), ballet corp (very hard to make it work)

This model is quite easy to use, just start your prompt with "a ballet dancer wearing ballet dress", add if you want "wearing tutu" and change the color as you want like "a ballet dancer wearing red ballet dress, wearing yellow tutu".

Keywords "in theater" and "in a studio" might give good results considering its a ballet dress and thats the proper environment for it.

regarding ballet corp keyword, i didn't manage to make it work even if many images of ballet corps dancing were used to train the model, you might give it a try and achieve what i didn't.

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