rzgar/Eva-Qwen-V4b-Qwen-Image-2512

🤗 On Hugging Facetext-to-imagemit724 MBother✓ Checksum-verifiedupdated 0d ago
Magnet

!Qwen-Image-2512_00001_.png

Eva Qwen

Model description

Eva Qwen v4b is a character LoRA for the latest Qwen-Image models. It is an upgrade from v4.

What was improved compared to v4

  • v4 issues: Looked very silky/smooth and felt slightly underfit.
  • New training:
  • Updated dataset with less perfect, torn, and filthy day-to-day clothing in a wide variety of real-life situations.
  • Much more detailed skin textures.
  • Used 5-Preview Detailer Hook Provider workflow to enhance fine details.
  • Higher network rank + slightly more conservative learning rate so the LoRA actually learns the details properly.

Results

  • Better, more natural skin quality
  • Much closer to the character's original facial identity
  • More realistic and varied clothing (including imperfect/torn/filthy everyday looks when prompted)
  • Overall more balanced and better output

For even better results, combine this LoRA with popular Qwen-Image fp8 merges.

Recommended fast inference: Use together with the lightx2v 8step LoRA:

Qwen-Image-2512-Lightning-8steps-V1.0-fp32.safetensors

Previous version (V4): Eva-Qwen-V4-Qwen-Image-2512

Older versions: r_drive

Trigger words

You should use Eva_Qwen to trigger the image generation.

Download model

Download them in the Files & versions tab.