Quantization of Kroma v0.3.1 OPD Turbo by Lodestones primarily meant for low VRAM/RAM usage, expect degradation in quality compared to INT8 Convrot Quants.
4 Step Lora has been merged at strength of 1 so use it at 4 steps instead of 8.
Used a simple T2I workflow, no second stage or upscaling done as I'm too lazy for that.
4 steps
CFG 1
Euler / Simple
Resolution 1