Model Introduction:
The model is designed to create clear paintings that take advantage of the feeling of niji6.
Instructions for use:
1. We recommend using 1024x1536 for the output resolution of XL.
2. Always include "masterpieces" and "best quality."
I use "(best quality, 4k, 8k, highres, masterpiece:1.2), (perfect hands, perfect anatomy), The highest image quality, excellent detail, ultra-high resolution, best illustration, attention to detail, exquisite beautiful face, detailed hands, expressive eyes, uncensored" prompts like this.
3. Use 2M or 3M series sampler with approximately 35 steps.
4. As for negative prompt words, you don't have to write too much.
I use "(worst quality, low quality:1.4), (malformed hands:1.4), (poorly drawn hands:1.4), (mutated fingers:1.4), (extra limbs:1.35), (poorly drawn face:1.4), bad leg, strange leg" prompts.
5.You do not need to use VAE.
6.CFG scale 2~5
Model Restrictions:
this model is a derivative of the SDXL 1.0 model and the following restrictions are part of the 2023 Stability AI CreativeML Open RAIL++-M License dated July 26, 2023, with applies to this model and all models that use any component or derivatives of this model.
