moss image style。lora-yomi

# YOMI Style — MOSS-Image LoRAA style LoRA for MOSS-Image, trained on the SFT checkpoint (thecheckpoint most people actually generate with), so there is notrain/inference distribution gap.## Trigger word&gt; *<code>yomi</code>**## Recommended prompt yomi, bold painterly brushstrokes, vibrant high-contrast colors, chunky color blocking, dynamic composition, iridescent light leaks, glowing rim light, 1girl, white background, looking at viewerThe style follows a modern theatrical-anime look: strong lineworkdissolved into colour blocks, high-contrast saturated palettes, andspecular highlights with iridescent light leaks.## Recommended settings| Setting | Value ||---|---|| Base model | MOSS-Image SFT (bf16) || LoRA strength | 0.8 – 1.0 || Sampler | Euler || Scheduler | simple || Steps | 50 || CFG | 3.0 || Shift | 5.0 || Negative-branch skip | layer 22 || Resolution | 1024×1024 or higher |Negative prompt (only active above CFG 1): worst quality, bad anatomy, watermark, jpeg artifactTip: with the 8-step DMD speed LoRA loaded at 0.7 and CFG 1,the LoRA still works but the style is noticeably softer. Use CFG 3when style fidelity matters.## Training details| Item | Value ||---|---|| Base | MOSS-Image SFT bf16 || Trainer | Fizgig v8.5.0 (open source) || Network | LoRA, attn + MLP || Rank / Alpha | 4 / 4 || Learning rate | 3e-4, constant with 20-step warmup || Optimizer | AdamW || Epochs / Steps | 20 / 1320 || Batch size | 1 || Resolution | 768 (0.59 MP) || Precision | bf16 || EMA | 0.98 || Dataset | 66 images, single style || Captions | WD14 content tags + fixed style description || Text encoder | frozen (DiT-only LoRA) || Output | 18.2 MB safetensors, 246 modules |Notes:- Trained on SFT, not Base — it patches the model you are actually loading, so strength behaves predictably.- DiT-only adapter: no CLIP/text-encoder weights are included.- Trained at 0.59 MP; it generalises upward but 1024+ gives the best line quality.- Works with the regular ComfyUI LoRA loader for MOSS-Image.

Files with SHA256: 0098b37260492eba2289fe1fa2357b516238d7f438493134b884a6e1e7a67c79