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.<hr />Suggested settings below:<ol><li>Trigger word: rmuk</li><li>CFG Scale: 6-7.5</li><li>Steps: 30-60</li><li>Strength: 0.8-1</li><li>Samplers: DPM++ 2S Karras, Euler a</li><li>Hires fix using the 4x-UltraMix_Balanced upscaler</li><li>ADetailer</li></ol>

Files with SHA256: 1a5fcbc74a879bbdebb925457caf961fb08fdbb04a66eb0ff6761300260fe0ff