Trained with 29 photos (8 face, 10 half body, 11 full body) - 10 epochs. Base Realistic Vision V6.0 B1.
**Trigger words: redwitch, mikaela reid dbd
Working config: 512x768, Steps: 6, CFG: 1.5, Sampler: DPM++ SDE Karras, Checkpoint: RealisticVisionV60B1_v51HyperVAE.safetensors, Weight: <lora:redwitch:0.7>
💡 My personal recommendation:
I trained and tested this LoRA with Realistic Vision V6.0 B1 HyperVAE, and that's where I like it the most.
That's where the skin, freckles and curly hair look the most natural, more like the real Mikaela.
If you try it with normal Realistic Vision (not HyperVAE) it also works, just at 25 Steps, CFG 7 it looks a little more polished, more like a studio photo. Personally I prefer the 6 steps version because it looks more natural and softer.
If you use it at 25 steps I recommend lowering the weight a little to 0.6 so it doesn't look too perfect: <lora:redwitch:0.6>
Description
Trained on 29 images (8 face, 10 half body, 11 full body) / 10 epochs / 512x768 / Base Realistic Vision V6.0 B1.
Best config testing: Strength 0.7, CFG 1.5, Steps 6, Sampler DPM++ SDE Karras, Clip Skip 1, Size 512x768.
From ugly face at 0.9 with big teeth to young slim realistic at 0.7 without 3 arms or rigid mannequin doll gray background. Faithful with black witch hat, nose ring, round thin glasses, copper curly red hair, forest background.
Trigger: mikaela reid, mikaela reid dbd
Recommended: (mikaela reid:1.2), (round thin glasses:1.2), (nose ring:1.2), slim petite 23yo