KatyB

Scale only UNet blocks above depth 2 → stronger adherence to prompt.

Slightly downscale text encoder adapters → better facial consistency in img2img.

Update metadata with tags so it loads cleaner in UIs (“img2img tuned,” “balanced strength,” etc.).

Recommended img2img settings (SD1.5)

LoRA weight: 0.7–0.9

Denoise strength: 0.20–0.40 (lower = tighter face match)

CFG: 3.0–5.0

Sampler/steps: DPM++ 2M Karras, 20–28 steps

Seed: reuse the source image’s seed when comparing variants

Extras (optional):

• IP-Adapter / FaceID: 0.6–0.8 for very high face lock

• ControlNet (Canny/Lineart): 0.35–0.55 to preserve composition/edges