Early holiday update with image training set increased to ~1100 images and lower epoch used, allowing for higher range/versatility of generations (recommended strength now 0.4 - 0.8). More of an incremental update, but should improve quality across the board, especially when combined with KFT Fur Elise Checkpoint. "kftenhance" tag suggested for minor improvements.
The next evolution of the KFT Fur / Scale / Scene Enhancer is here! Built from the ground up utilizing a large variety of realism focused images using multiple checkpoints and KFT FSSE V5 Realism, this LORA delivers the fluffiest fur, scaliest scales, and most feathery feathers available on the PonyXL V6 marketplace
*.
This enhancer aims to get rid of the 'clothing/seam factor' that many checkpoints/models suffer from, where instead of getting proper fur, it looks like a fuzzy costume. It also targets optimizing furry features like paws, snouts, fangs, wings, scales, etc. as much as a LoRA can do (often checkpoint dependent). This model is quite powerful, and depending on the checkpoint/character you're trying to make, you may only need 0.3 - 0.4 model strength for good results! (See Examples/Strength Comparison Gallery below)Recommended Strength: 0.3 - 0.8 (depending on type of character and checkpoint used: experiment!)
Sampler: DPM++ 2M Karras / DPM++ 3M Karras (GPU seeded) (Euler A gives much worse fur quality with most tested checkpoints)
Tags: "kftenhance" (optional tag - may enhance certain features), "furry"
