Can’t say it turned out like I was hoping at all.
Description
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
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.