First attempt at a LoRA on CivitAI. Trained locally using sd_scripts @ 1024x1024 resolution. 20 image dataset trained for 70 epochs. Works best for me using the dpmpp_2s_ancestral beta sampler in ComfyUI @ 0.8 strength with 2.5 - 2.8 Flux guidance.
https://www.instagram.com/evieleemikomin/
Description
1024x1024 only token, 1400 steps.