LoRA Model Card: svjack/Prince_Xiang_Z_Image_Turbo_Lora
Character Wang Xiang, Art Synthesis with Aesthetic Portraits
Fine-tuned Adapter: Xiang_HairCut_Gls_ZIT_Lora_000004750.safetensors
Base Model: Z-Image-Turbo
Core Strengths:
- Character Consistency: Maintains detailed facial features (fair skin, subtle facial contours) across diverse settings and lighting conditions.
- Aesthetic Detailing: Captures delicate textures of skin, hair, and fabrics with nuanced lighting effects.
- Dynamic Poses: Handles complex human poses with natural anatomical proportions and expressive gestures.
- Adult Artistic Style: Sensual artistic style through sexy pose, fabric movement and lighting.
Inference Dataset: demonstrates inference samples of this lora model.
- https://huggingface.co/datasets/svjack/Prince_Xiang_Z_Image_Turbo_glasses_Images
- https://huggingface.co/datasets/svjack/Prince_Xiang_Z_Image_Turbo_different_style_Images
Optimized Text-to-Image Prompts
Example 1: Intellectual Elegance
Prompt:
王翔戴着深蓝色细框窄边细眼镜，镜片后深邃的眼眸泛着微光，
浅灰色高领帽衫垂落的衣角随着他垂眸时的呼吸微微起伏，
露出锁骨处若隐若现的皮肤光泽。他指尖无意识地摩挲着帽衫褶皱，
腕表带滑过手背时带起一阵若有似无的香气，
垂落的发丝扫过锁骨凹陷处，喉结在吞咽动作中泛起微红，
睫毛在眼下投出细碎阴影，仿佛随时会从镜片后溢出灼热的凝视。
Key Characteristics:
- Accessory Detailing: Glasses and watch are rendered with material accuracy
- Lighting Control: Subtle shadows and highlights create depth
- Texture Quality: Fabric folds and skin surfaces show high-frequency details
Example 2: Winter Scene
Prompt:
王翔站在雪地中央，深黑色风衣下摆被寒风掀起一角，
露出内衬的黑色毛衣勾勒出修长的身形轮廓，
白围巾垂落至腰际，雪色绒毛在冷光中泛着柔光。
他微微侧头凝视镜头，睫毛在面颊投下细碎阴影，
指尖无意识地摩挲着风衣扣子，喉结随着呼吸轻轻起伏，
白皙皮肤在雪地映衬下透出冷冽光泽。
当雪粒掠过他垂落的发梢时，他忽然抬手将围巾轻轻挽起，
露出锁骨处若隐若现的肌肤，指尖划过下巴时，
唇角扬起一抹慵懒的弧度，仿佛整个冬日的寒意都凝固在他凝视镜头的瞬间。
Key Characteristics:
- Environmental Integration: Character naturally blends with winter elements
- Color Contrast: Black clothing against white snow creates visual impact
- Dynamic Elements: Snow particles and fabric movement add life to the scene
Example 3: Aquatic Atmosphere
Prompt:
王翔，一米八修长身高，戴着银框窄边细眼镜,正对镜头,
指尖轻点游泳池水面荡开涟漪，
喉结在湿润的肌肤下若隐若现，唇角勾起慵懒弧度凝视镜头，
上身穿着白色背心，腰腹处白色三角内裤勾勒出若隐若现的轮廓，
水珠顺着锁骨滑落锁骨凹陷处。
Key Characteristics:
- Atmosphere: Intimate setting with reflective surfaces
- Composition: Close-up framing emphasizes facial expressions and water interaction
Example 4: Coastal Portrait
Prompt:
王翔，正面面向镜头，白皙的肌肤在阳光下泛着柔和的光泽，
黑色半截袖勾勒出修长的臂膀，
袖口微微卷起露出细腻的手腕。他慵懒地倚着礁石，
黑色三角内裤在海风中若隐若现，
腰线处的弧度随着他轻抬下巴的动作若隐若现。海浪声中，
他忽然侧头露出耳后迷人的弧度，
发丝被海风吹起时露出锁骨处浅浅的酒窝，
指尖无意识地摩挲着被晒得微红的脚踝，尾音带着挑逗的笑意。
Key Characteristics:
- Lighting: Soft sunlight enhances skin texture and creates natural shadows
- Composition: Casual pose against coastal elements creates dynamic framing
- Details: Focus on subtle anatomical features and fabric textures
Example 5: Glasses Style Grid
Inference Style Dataset: demonstrates inference samples of this lora model in glasses style.
https://huggingface.co/datasets/svjack/Prince_Xiang_Z_Image_Turbo_glasses_Images
Xiang Glasses Grid Image
Example 6: Different Style Grid
Inference Style Dataset: demonstrates inference samples of this lora model in different style.
https://huggingface.co/datasets/svjack/Prince_Xiang_Z_Image_Turbo_different_style_Images
Xiang different style Grid Image
Technical Parameters
| Setting | Recommendation | Notes |
|---|---|---|
| Resolution | 1280×2048 | Optimal for portrait details |
| CFG Scale | 7.0 | Balances creativity & anatomical accuracy |
| Sampler | DPM++ 2M Karras | Preserves skin textures and fabric details |
| Steps | 8-20 | Ensures facial feature and clothing fidelity |
| LoRA Weight | 0.9-1.1 (init with 1.0) | Adjust for desired character strength |
Performance Profile
- VRAM Consumption: ~18-22GB (depending on base model)
- Inference Speed: Optimized for Z-Image-Turbo's efficient architecture
- Training Data: Focused on character consistency and aesthetic portraiture
Usage Guidelines
Trigger Words
- Use "王翔" as the primary trigger for character consistency
- Include descriptive terms for specific aesthetics (e.g., "soft lighting", "water droplets", "snow particles")
Weight Adjustment
- 0.7-0.8: Subtle character influence, blends with base model style
- 0.9-1.0: Strong character presence, maintains distinctive features
- >1.0: Experimental, may enhance specific characteristics
Compatible Models
Designed for optimal performance with Z-Image-Turbo base model, but compatible with other realistic vision models through weight adjustment.
License
CC-BY-NC-SA 4.0 (Non-commercial, share-alike)
Community Hub: https://huggingface.co/svjack/Prince_Xiang_Z_Image_Turbo_Lora/discussions
Training Methodology
This LoRA adapter was trained using low-rank adaptation techniques focusing on:
- Character Consistency: Maintaining stable identity and features across varied prompts. character has face:
- Texture Quality: Enhanced skin, hair, and fabric rendering
- Pose Variety: Supports multiple angles and expressions while preserving identity
The model demonstrates Z-Image-Turbo's capabilities in handling complex human portraits with aesthetic sensitivity, particularly excelling in lighting and texture reproduction.