AIが動く。未来が更新される。krea2-turbo-sda
A rank-32 LoRA for Krea 2 Turbo that **restores the sampling diversity the Turbo distillation removed**, without degrading image quality or prompt adherence. Trained with **SDA (Semantic Directional Alignment)** — a teacher-guided diversity alignment loss — wrapped in **Forward XM best-of-5** candidate exploration, on a single high-noise sigma node (σ = 0.9567). *"a cat sitting on a windowsill"* — the baseline regenerates the same tabby-and-white cat 16 times; the LoRA varies fur patterns, lighting, seasons and window settings: *"a still life with fruit on a table"* — one pineapple-centric template vs varied compositions, props and backgrounds:
翻訳準備中のため原文を表示しています
A rank-32 LoRA for Krea 2 Turbo that **restores the sampling diversity the Turbo distillation removed**, without degrading image quality or prompt adherence. Trained with **SDA (Semantic Directional Alignment)** — a teacher-guided diversity alignment loss — wrapped in **Forward XM best-of-5** candidate exploration, on a single high-noise sigma node (σ = 0.9567). *"a cat sitting on a windowsill"* — the baseline regenerates the same tabby-and-white cat 16 times; the LoRA varies fur patterns, lighting, seasons and window settings: *"a still life with fruit on a table"* — one pineapple-centric template vs varied compositions, props and backgrounds: