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:
35 images, 20 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 10
LORA weight for txt2img: reccomended 0.2-0.7 (i used 0.5 in my images).
Keys: oversized_jacket
Try to start your prompt with you girl model and then "(wearing oversized_jacket:1.3)" might work without any weight but in my experienced gives best result with 1.3 weight on the keyword and 0.5 weight on the model.
I did 12 epochs but i'm uploading the 1st one, only 20 steps per image total. If you want to try other epochs come in my Patreon and download all of them.
Checkpoint used to generate the images: Chillout for realistic ones/Yesmix for anime ones
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