AnyLoRA - Checkpoint
Updated 2/14/2025
About this model
AnyLoRA is a model designed to ensure LoRA training compatibility with newer models, providing a style-neutral base for accurate style representation. It excels at training and inference, especially with anime styles, and consumes little VRAM; use pruned versions for training. It is recommended to use CLIP skip 2 and booru style tags when training, along with a good VAE for optimal image saturation.
Version: noVae fp16
AnyLoRA - Checkpoint noVae fp16
Posts with this model
No posts found for this model version. Be the first to create something with it!