Krea2 turbo

Uploaded as Version 0.1 for testing Krea2 LoRA generation.

Z-Image turbo

Uploaded as Version 0.1 for testing ZIT LoRA generation. All sample images were generated using Z-Image Power Nodes, with FlashVSR used as the detail enhancer.

Usage

• Trigger word: jpwmn01

• Recommended model strength: 1.0 (ZIT), 0.8 (Krea2)

• CLIP/Text Encoder connection is not required.

Disclaimer

• This model is intended for creating the faces of fictional adult Japanese women.

• This model does not depict any real person.

• The creator assumes no responsibility for generated content or misuse of this model.

• Users are solely responsible for the content they generate with this model.

Training Information

• Trained with AI-Toolkit using 17 images for 600 steps on an RTX 3060.

• This LoRA was trained as UNet-only. CLIP / Text Encoder training was disabled.

私の初めてのLoRA作成は、こちらのYouTube動画を参考にしました。（日本人向け）

ダルトワ★TVさんありがとうございます。