ModelsLab/Hon Kitsune Ai - VTuber - SDXL 1.0 - SDXL 1.0

Hon Kitsune Ai LoRA SDXL 1.0 (v1.0) Version changes / notes (SDXL 1.0 port)Re-trained from scratch on SDXL 1.0 base model (not merged / no DreamBooth conversion).Image set expanded : 80 imgs @ 1024 × 102430 close-up · 25 half-body · 25 full-body.Higher network capacitynetwork_dim 192 · network_alpha 96 ( 65 MB).Optimiser & scheduleAdafactor · LR 8e-4 (UNet) / 2e-5 (CLIP-G) · cosine with restarts × 4.Training tricksMin-SNR = 5, noise offset 0.05, flip aug., colour jitter light.Bucketed aspect ratios up to 1152 px handles vertical character shots better.Recommended LoRA weight0.55 0.7 portraits · 0.65 0.85 full-body (SDXL needs a bit more).Trigger unchanged hono_kitsune_ai.Works best on Checkpoint SDXL-TurboMix / Juggernaut XL but any SDXL 1.0 compliant base is fine.