| A stylized LORA model trained with ~200 images by Puuzaki Puuna. The 784mb VAEs (NAI, Orangemix, Anything, Counterfeit) are recommended. 0.6~0.8 weights should be enough. Some output images may be watermarked, which can be prevented by adding 'signature', 'artist name' and 'watermark' in the negative prompt. | |
| puuzaki puuna，shiny skin，shiny |