This LoRA is designed to improve the depiction of characters with animal ears (such as cat ears, dog ears, etc.) by suppressing the generation of human ears. When using this LoRA, human ears are effectively removed or not rendered, making the character's appearance more natural and consistent with the presence of animal ears. Both Illustrious version and Pony version are available. Switch version tab above↑ to choose matching type for your checkpoint. This LoRA is suitable for 2D-2.5D illustrations only and not suitable for photorealistic checkpoints. My "Breed" series checkpoints will make good outputs. Sample images are generated with "Breed" series listed on "Suggested Resources" section. This LoRA is developed by a new training method called "ADDifT" (Japanese written article), implemented in TrainTrain extension.