Downloads · 30 days
0
Prince_Xiang_Z_Image_Turbo_Lora
svjack/Prince_Xiang_Z_Image_Turbo_Lora
Prince_Xiang_Z_Image_Turbo_Lora is a machine learning model from svjack. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Fine-tuned Adapter: - XiangHairCutGlsZITLora000004750.safetensors - XiangPhotoshootZITLora000005750.safetensors - PrinceXiangwhbflora000004500.safetensors - PrinceXiangslimfacelora000002000.safetensors - Xiang-Dream-Z…
Access
Public
Updated Feb 12, 2026
Repo size
2.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.7 GB · 100%
At a glance
- Access
- Public
- Created
- Dec 22, 2025
- Updated
- Feb 12, 2026
- SHA
- 35c50d94
Model card
From the Hugging Face model README
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
- Xiang_Photoshoot_ZIT_Lora_000005750.safetensors
- Prince_Xiang_whbf_lora_000004500.safetensors
- Prince_Xiang_slim_face_lora_000002000.safetensors
- Xiang-Dream-ZIT-Lora_000001750.safetensors
- Xiang_bottom_ZIT_Lora_000002000.safetensors
- Prince_Xiang_noclothes_ZIT_Lora_000002000.safetensors
- Xiang_Dream_nocloth_ZI_Lora_000002000.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/Xiang_Watermelon_Hair_Cut_Videos_DreamID_V_Face_Swap
- https://huggingface.co/datasets/svjack/Peng-With-Xiang-SkyReels-V3-Videos
- https://huggingface.co/datasets/svjack/Xiang_Furry_Z_Image_Turbo_videos
- https://huggingface.co/datasets/svjack/Prince_Xiang_Z_image_turbo_Photoshoot_tease_images
- https://huggingface.co/datasets/svjack/Prince_Xiang_Z_Image_Turbo_hoodie_Tease_grid_images
- https://huggingface.co/datasets/svjack/Prince_Xiang_white_brief_Z_Image_Turbo_tease_videos
- https://huggingface.co/datasets/svjack/Prince_Xiang_Z_Image_Turbo_tease_videos
- https://huggingface.co/datasets/svjack/Prince_Xiang_Z_Image_Turbo_tease_images
- https://huggingface.co/datasets/svjack/Prince_Xiang_Z_Image_Turbo_slim_images
- 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: 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 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 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 3: 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 2: Face Swap Grid Video
- Xiang Reference Image
- Face Swap Grid Video
- https://huggingface.co/datasets/svjack/Xiang_Watermelon_Hair_Cut_Videos_DreamID_V_Face_Swap <video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/UdnaLoTga1RifjPjKSRZE.mp4"></video>
Example 3: Peng and Xiang Kiss Grid Video
- Peng Reference Image
- Peng and Xiang Kiss Grid Video
- https://huggingface.co/datasets/svjack/Peng-With-Xiang-SkyReels-V3-Videos
<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/fbIo3D-XIimJW2H3renwN.mp4"></video>
Example 4: Tease Grid Image
Inference Style Dataset: demonstrates inference samples of this lora model in tease style.
Example 5: Tease Grid Video
Inference Style Dataset: demonstrates inference samples of this lora model in tease style.
-
https://huggingface.co/datasets/svjack/Prince_Xiang_white_brief_Z_Image_Turbo_tease_videos
-
Xiang Tease Grid Video
<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/NSK_oGi6_AgXZUwNmqCNV.mp4"></video>
Example 6: Tease Grid Video
Inference Style Dataset: demonstrates inference samples of this lora model in tease style.
-
https://huggingface.co/datasets/svjack/Prince_Xiang_Z_Image_Turbo_tease_videos
-
Xiang Tease Grid Video
<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/S8M0bUyw_ymbP3XILUNAB.mp4"></video>
Example 7: Furry Style Video
<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/bicGP7xkCi4BmHxNuQGm8.mp4"></video>
Example 8: Slim 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_slim_images
-
Xiang Slim Grid Image
Example 9: 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 10: 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
<!-- ### Example 6: Qwen-Image-i2L (image to lora) Different Style Transform Grid **Inference Style Transform Dataset**: demonstrates inference samples of images produced by this lora model in different style transformed by Qwen-Image-i2L. - https://huggingface.co/datasets/svjack/Xiang-Style-Transfer-Qwen-Image-i2L - Xiang different style Grid Image Transformed by Qwen-Image-i2L - Upper as Style reference, Lower left as Source Image, Lower right as Target Image  --- ### Example 7: Xiang Sports Qwen-Image-i2L (image to lora) Different Style Grid Videos **Inference Style Transform Video Dataset**: demonstrates inference samples of images produced by this lora model in different style transformed by Qwen-Image-i2L into sports video. - https://huggingface.co/datasets/svjack/Xiang-sports-Qwen-Image-i2L-Videos - Xiang Sports Qwen-Image-i2L Style Grid Video <video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/634dffc49b777beec3bc6448/Px-XIieP4SBFegNeQ5lE6.mp4"></video> --- ### Example 8: Adult Artistic Tease Grid **Inference Tease Dataset**: demonstrates inference samples of this lora model in sexy tease pose domain. - https://huggingface.co/datasets/svjack/Xiang_Z_Image_Turbo_Tease_Images - Xiang Tease Grid Image <img src="https://huggingface.co/svjack/Z_Image_Turbo_Xiang_Lora/resolve/main/xiang_tease_grid.png"></img> --- ### Example 9: POV Touch Grid **Inference POV Dataset**: demonstrates inference samples of this lora model in pov pose domain. - https://huggingface.co/datasets/svjack/Xiang_POV_Touch_Z_Image_Turbo_Images - Xiang POV Touch 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.
- Created
- Dec 22, 2025
- Updated
- Feb 12, 2026