Trained on AnimaPreview3.
Best result with weight between : 0.8-1.

I recommend to use it with Adetailer. Otherwise you will need to inpaint.
Suggested workflow is :
- no LoRA in base txt2img prompts with prompt for eyes
- Activate Adetailer 1st with face_yolov8n.pt full prompts + LoRA to redo the face
- Activate Adetailer 2st with PitEyeDetailer-v2-seg.pt with only eyes prompts + LoRA to redo only the eyes.

Commissioned on kofi

Reviews are really appreciated, i love to see the community use my work, that's why I share it.
If you like my work, you can tip me here.

Got a specific request ? I'm open for commission on my kofi! If you provide enough data, OCs are accepted

If you want to get updates on my projects as they go, you can follow me on X