π¬ MY SETTINGS π¬
πΈ CLIP SKIP: 2
π² CFG Scale: 4.5 | 5 | 5.5 | 6 (Optimal)
π§Ό Samplers / Schedulers: Euler A, DPM++ 2M SDE, SGM Uniform, BETA, Karras
π£ Steps: 20 β 40
β¨οΈ Hi-Res Fix: 4x-UltraSharp or Foolhardy Remacri (Don't use it now)
π Adetailer: Use for Face and Eyes if you have problems with them
Description
π§ΌNaithhy - Boost Japan Styleπ§Ό
Β§π₯LoRA version.π₯
𧬠Technical Specifications
ββββββββββββββββββββ³βββββββββββββββββββββββββββββββββ
β β³ Model Version: γ €γ €β v/Stable [1.0] γ €γ €γ €γ €γ €γ €γ €γ €γ €β
β£ββββββββββββββββββββββββββββββββββββββββββββββββββββ«
β β³ Training Dataset: γ €β 92 High-Quality Images γ €γ €γ €β
β£ββββββββββββββββββββββββββββββββββββββββββββββββββββ«
β β³ Primary Focus: γ €γ €β Style & Effects + LoRA Slider β
ββββββββββββββββββββ»βββββββββββββββββββββββββββββββββ
β¨ What's Improved
LoRA has its own character drawing style, no trigger words are needed β you can see what style it is in the preview images.
My recommendation is 0.8 strength, but by default I always set it to 1.
The preview images are always at full LoRA strength [1.0].