lacoz Asian girl Face LoRA (Realistic Vision v5.1 vae base) Part 3

lacoz Asian girl Face LoRA (Realistic Vision v5.1 vae base) Part 3
Base Model Link: Realistic Vision v5.1 vae base

This LoRA is trained by blending the faces of two Asian women.

The recommended LoRA weight is fixed at 0.7.

---

🔹 Trigger

Trigger word: lacoz

When using the lacoz trigger, the LoRA’s identity becomes stronger and more defined.
Even without the trigger, the face blends naturally into the base model and remains consistent.
Feel free to use the trigger—or not—whichever works best for your workflow.

---

🔹 Technical Info

Training Environment: LoRA training using kohya sd-scripts.
Kohya-trained LoRAs work just fine in A1111 :)
Runtime UI: ComfyUI
Recommended Nodes:
LoraLoaderModelOnly
LoraLoader
CLIPSetLastLayer
Recommended LoRA Weight Range: 0.7

---

🔹 Notes

Facial distortion may occur if the latent image resolution is low, or if the face appears too small within the latent image.
In such cases, using FaceDetailer is recommended. 🙂

Face distortion issues?
→ Fix Face Distortion in ComfyUI (FaceDetailer Guide) | Civitai

---

☕ Support

If you find this LoRA useful, your support is always appreciated:
https://buymeacoffee.com/lacoz