Note: LoRAs work to different degrees on different checkpoints. Don't leave a bad review because you used a random checkpoint that was overtrained on another face and consequently mucked up the output. Constructive feedback, on the other hand is always welcome.

Suggested settings below:

1. Trigger word: rmuk

2. CFG Scale: 6-7.5

3. Steps: 30-60

4. Strength: 0.8-1

5. Samplers: DPM++ 2S Karras, Euler a

6. Hires fix using the 4x-UltraMix_Balanced upscaler

7. ADetailer