This style LoRA was trained using 180 carefully selected images.
For best results, use a weight of 0.7–1.0 when using this LoRA alone. When combining it with other style LoRAs, feel free to lower the weight as needed.
Prompts
artist:arshillustrationstyle,Please format your prompts using trigger words followed by natural language. All example images include ComfyUI workflows embedded and can be dragged directly into ComfyUI for use.
V2.0➡️Adjusted the training parameters again and trained for more steps; the art style and details are now much more faithful to the original.
V1.0➡️Fully trained with optimized hyperparameters and training steps.
V1.0test➡️This is a test version. Using new parameters and more training steps clearly yields much better results, though these might not be the optimal settings yet, so I'll keep testing. Also, keep in mind that since this is a test build and the dataset tagging inherits Anima's scheme, the model's text comprehension might be slightly reduced. I will retag the data and retrain it for the official release.