ModelsLab/Jun Park - Last Reader Standing - SDXL 1.0

Version 1.0 Initial release (SDXL)What s new / changedFresh training from scratch on 26 high-resolution images (1024²) covering Jun s signature outfit ( 80 %) and casual looks ( 20 %).Base checkpoint: SDXL 1.0.Kohya pipeline:network dim 32 / alpha 16 ( 55 MB)520 steps over 10 epochsUNet LR 5 × 10 · Text Encoder LR 5 × 10 cosine LR scheduler (3 restarts) · min-SNR = 5 · noise offset = 0.1smart buckets ON, clip-skip 1, batch 4Trigger words: JunPark (LRS) or JunParkLRSAdd JunPark Outfit or JunPark Casual Outfit for clothing control.Recommended weight: 0.7 0.9 (txt2img) · denoise 0.55 0.65 (img2img).Compatible with any SDXL-based checkpoint.Known quirksVery close-up portraits may soften pendant detail; add sharp pendant or lower CFG.Extreme dynamic poses can introduce minor hand artifacts at strength > 0.9.Roadmapv1.1 (planned) dim 64 / alpha 32 build with ~50 image dataset for sharper close-ups and broader lighting variety.Enjoy bringing Jun Park to life feedback is welcome!