This Lora is not good enough as I would like it to be. I ran over 25 tests with different settings and dataset adjustments, but I couldn't get anything better.It took so many tries most likely because of the limited dataset, so I used also screenshots from Koikatsu to train this Lora.LoRA is designed for use with AutismMix SDXL or other mixModel: ponyDiffusionV6XL_v6.safetensorsDataset size: 48Clip skip: 1dim32, alpha16unet_lr=0.0001te_lr = 0.00005Constant, AdamWmin_snr_gamma: 7.0My tips for generating on SDXL for AUTOMATIC1111Resolution:1024 x 10241152 x 896 or 896 x 11521216 x 832 or 832 x 1216Don't use Hires. fix. Send the picture to img2img, set CFG 0.15-0.25, then select “SD upscale” in the script, you also need to select 4x-AnimeSharp (find out how to install it) or what you like best from upscale. All other settings are default. Click generate.For me 12gb VRAM is enough for this using --xformers
