YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

LoRA Model Card: svjack/Xiang_Flux2_klein_Lora

Character Wang Xiang, Art Synthesis with Aesthetic Portraits

Base Model: flux-2-klein-base-4b.safetensors

Fine-tuned Adapter:

  • Xiang_Dream_Nocloth_klein_4B_Lora_000011750.safetensors
  • Peng_YangYang_klein_4B_Lora_000002500.safetensors
  • Flux2-klein-4B-depth-lora_000000750.safetensors

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.


Example 1: Head Swap And Multiscene Photoshoots

  • Xiang Reference Image

头部捕获

ComfyUI_temp_lzksj_00002_


Example 2: Hoodie Butt

ComfyUI_temp_jrron_00001_


Example 3: Peng and Xiang Grid Video

  • Peng Reference Image

志鹏头部捕获


Example 4: Nocloth Grid Images

ComfyUI_temp_nzuyo_00003_

ComfyUI_temp_iaqdm_00002_


Example 5: White brief Grid Video


Example 6: Sport Grid Video


Example 7: Daliy Grid Images

ComfyUI_temp_tvmxl_00001_


Technical Parameters

Setting Recommendation Notes
Resolution 1280×768 Optimal for portrait details
CFG Scale 7.0 Balances creativity & anatomical accuracy
Sampler DPM++ 2M Karras Preserves skin textures and fabric details
Steps 20 Ensures facial feature and clothing fidelity
LoRA Weight 0.9-1.1 (init with 1.0) Adjust for desired character strength

License

CC-BY-NC-SA 4.0 (Non-commercial, share-alike)
Community Hub: https://huggingface.co/svjack/Xiang_Flux2_klein_Lora/discussions

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support