rzgar/Qwen-Image-Edit-smoothify

🤗 On Hugging Facetext-to-imagemit767 MBother✓ Checksum-verifiedupdated 0d ago
Magnet

Qwen-Image-Edit Smoothify (NSFW-Aware))

Model description

Qwen-Image-Edit Smoothify (NSFW-Aware)

This LoRA fine-tunes Qwen-Image-Edit to apply a vibrant, semi-realistic anime fashion style to realistic input images.

Style features:

  • Smooth cel-shading, large glossy eyes, flowing hair with highlights.
  • High-saturation colors (bold purples, yellows, whites), soft glows, and gradients.
  • Dynamic streetwear poses: crop tops, shorts, belts, thigh-highs, accessories, urban backdrops.

Primary goal: Transform realistic portraits/full-body photos into playful, glamorous anime art , with strong pose and body proportion accuracy.

Dataset includes NSFW content for training precise body topology and clothing fit (tight outfits, skin exposure). This improves 75–85% pose/body accuracy in stylized outputs, especially in challenging angles and form-fitting attire.

Limitations & Safety

  • Not safe for unrestricted use.
  • Avoid inputs with minors, non-consensual themes.

Trigger words

You should use apply smoothify effect to the image to trigger the image generation.

Download model

Download them in the Files & versions tab.