Pony Realism compelled me to return. Hope you enjoy :)
Read Me!
This LoRA "appears" to be overtrained, however it is simply more sensitive to trigger words at higher strengths (0.9-1)
This LoRA is EXCELLENT at adding skin detail around 0.5 strength
You can then inpaint or ADetailer for ultra-accuracy at strength = 1
Trained on Pony Realism v2.1
CFG 3-4 works better than recommended CFG 6-7
Use "fingers" in negative if you want to avoid hands
Same dataset & captions as original ClitPussy1
Recommended Settings
Model: Pony Realism v2.1
Steps: 20-30
CFG: 3-4
Height/Width: any SDXL values
LoRA strength: 0.2-1 (higher = more closeups)
ADetailer
Description
26 images, varying aspect ratios
FAQ
Comments (2)
Oh, my God, that's great.
Can you share the training data?
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.