A style with fairly strong line-work and colors with a chibi touch.
How to use
Just prompt away as normal. Things to try is putting "3D" and/or "realistic" in negatives if your model has a lot of that mixed in. You can also try adding "chibi" as positive tag at various strength. Dataset contains mainly various monster/demon/etc girls, predominately with horns, so the LoRA is especially good at that but it works well with standard issue girls as well.
Don't forget to review and upload your own images, it's always fun to see what you're creating!
Like my LoRAs and want more? Please consider a small tip towards my electricity bill and further training >.<
MISC
Trained on NAI at 768 resolution with a dataset of 98 images.
All images are raw txt2img upscaled without any helper embeddings.
描述:
Initial Release
训练词语:
名称: Matsuda.safetensors
大小 (KB): 73850
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
