<h2 id="english">English</h2>A style slider for MOSS-Image-SFT that moves images between modern anime illustration and realistic photography. Negative weights → anime; positive weights → photography; 0 → base-model output. Start at -1.0 or +1.0 and adjust to taste. No trigger words are required.Recommended sampling<ul><li>Sampler: er_sde · Scheduler: simple</li><li>Steps: 25 · CFG: 3 · Resolution: 1024 × 1024</li><li>SLG: uncond skip, layer 26 (0-indexed), start 0.0, end 1.0</li><li>Apply LoRA to the model only; CLIP strength 0. Negative prompt: empty.</li></ul>Feel free to leave comments and share photos.<h2>中文</h2>适用于 MOSS-Image-SFT 的画风滑块，可在现代日式动漫插画与真人摄影质感之间调整。负数偏动漫，正数偏摄影，0 为底模原始效果。建议从 -1.0 或 +1.0 开始，按喜好调整，无需触发词。推荐采样设置<ul><li>采样器：er_sde；调度器：simple</li><li>步数：25；CFG：3；分辨率：1024 × 1024</li><li>SLG：uncond skip，第 26 层（从 0 计数），起止区间 0.0–1.0</li><li>LoRA 仅作用于模型，CLIP 强度为 0；负面提示词留空。</li></ul>欢迎多多留言，晒图。

MOSS Anime ↔ Realistic Slider

Initial release. A style slider for MOSS-Image-SFT: negative weights toward anime illustration, positive weights toward photography. No trigger words; model-only LoRA with CLIP strength 0. See the model description for recommended sampling settings.

Files with SHA256: b4d85bd8f0eccf31bb9cdd89f39c31f6aa5de2c0e793594bd4911b5e752aecdd