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.<a target="_blank" rel="ugc" href="https://www.instagram.com/evieleemikomin/">https://www.instagram.com/evieleemikomin/</a><a target="_blank" rel="ugc" href="https://www.patreon.com/mikomin">https://www.patreon.com/mikomin</a><a target="_blank" rel="ugc" href="https://x.com/MikominCosplay">https://x.com/MikominCosplay</a>

Files with SHA256: 76700f4eb1e0745b57b340a124a539745af0f3217f5b111ae261c89f73c2c844