RandyFox
Trained this a few days ago on Plumlucky art from twitter, V1 Using Zack3D as a base and V2 using NAI base. Works well on merges including/with Zack3D/NAI as well. Trained with many tags using the E621 Convnext tagger (Also by Zack).
Big thanks to the people who make LoRa guides, especially the one in the Furry Diffusion discord server for helping me understand this mess. Also thanks to Plumlucky for tweeting this out, gave me a boost <3
Popularity
Info
Latest version (V2.0 FR): 1 File
About this version: V2.0 FR
A version for the absolutely amazing FurryRock model. (https://huggingface.co/lodestones/furryrock-model-safetensors) made using fluffyrock-576-704-832-lion-low-lr-e18-offset-noise-e3 trained at 704 using a new method im trying. Its trained as a dreambooth and then extracted to a LoRa. Allows me to vary the dimensions to get best quality and size.
3 Versions
Go ahead and upload yours!
