







The model is available in three distinct versions, each tailored to specific use cases:
raw: A direct merge of base models without additional enhancements. This version is ideal for users who wish to perform further merging or customization.
base: Incorporates improved ???????, optimized for compatibility with LORA, a technique for fine-tuning pre-trained models.
styled: Features enhancements in both ??????? and visual aesthetics. While it may not integrate as effectively with LORA, it delivers slightly more appealing results.
To achieve optimal results with this model, use the following prompts:
very awa, masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, absurdres, newest, highres,worst aesthetic, good quality, normal quality, low quality, bad quality, worst quality, mid, early, old, human, multiple tails, oldest, lowres, bad ???????, bad hands, missing fingers, extra digit, fewer digits, very displeasing, sketch, jpeg artifacts, signature, watermark, username, adversarial noise, ai-generated, ai-assisted, stable diffusion,1. Hak untuk model yang diposting ulang adalah milik pembuat aslinya.
2. Pencipta asli yang ingin mengklaim model harap hubungi staf SeaArt AI melalui saluran resmi. Klik untuk mengklaim
