✨📸 CROWN Douyin Beauty Influencer & Alluring OOTD Photo Realism | MOSS-Image

[English]
Trained by NineCrowns ([CROWN]) at native 1024×1536 on an 8×NVIDIA B200 cluster (Rank 64 / Alpha 64) across 355 perceptual-dHash deduplicated, unwatermarked high-resolution Douyin beauty & fashion portraits organized into two dedicated sub-buckets:

1. Close-Up Pure-Desire Beauty Portraits (crown_douyin_babe, crown_babe_face): Delivers refined East Asian influencer V-line facial bone structure, luminous warm-porcelain skin micro-texture, crystal iris catchlights, and natural glossy lips.
2. Three-Quarter & Medium-Full Alluring OOTD Fashion Shots (crown_douyin_babe, crown_babe_ootd): Maintains the exact same high-beauty facial aesthetic and unified warm-porcelain complexion in medium/three-quarter OOTD framing with clean 5-finger hands, rich knit/silk/velvet fabric textures, and crisp deep-focus backgrounds.
3. Native ComfyUI Split Q/K/V Format: Directly compatible with ComfyUI MOSS-Image LoRA loaders.

[中文说明]
由 NineCrowns ([CROWN]) 基于 355 张经过感知哈希（dHash）严格去重与人工逐张清洗的高清无水印抖音纯欲美女与爆款穿搭图文写真，在 8×NVIDIA B200 集群上以原生 1024×1536 分辨率、Rank 64 / Alpha 64 双分桶精炼而成的 MOSS-Image 写真风格 LoRA：

1. 近景怼脸纯欲神颜特写（crown_douyin_babe, crown_babe_face）：精准还原顶级抖音颜值博主精致骨相、通透暖白瓷肌微毛孔质感、清澈眼神光与水润唇妆。
2. 中景/七分身爆款穿搭 OOTD 写真（crown_douyin_babe, crown_babe_ootd）：确保中远景全身/半身穿搭照与近景特写共享完全一致的高颜值审美与统一暖白肤色，五指自然修长清晰，背景全景深锐利真实。
3. 原生兼容 ComfyUI：标准拆分 proj.{q,k,v} 键位，直插 ComfyUI 即用。

• Base Model (底模): moss_image_sft_bf16.safetensors + qwen3.5_9b_bf16.safetensors + flux2-vae.safetensors
• Resolution & Sampler (分辨率与采样): 1024×1536, 28–30 steps, shift: 5.0, CFG: 3.5
• LoRA Weight (推荐权重): 0.85 ~ 0.95 (All 8 showcase portraits generated at 0.90)
• Trigger Words (触发词): crown_douyin_babe (+ crown_babe_face for close-ups, crown_babe_ootd for OOTD body shots)