SilvermoonMix03 focuses on abstract elements and dynamic contents. Abstract elements such as hair, water, or ribbon; detailed background and foreground; dynamic poses and angles can effectively demonstrate these.

For instructions on how to use the V-pred model, please refer to https://civitai.com/models/833294/noobai-xl-nai-xl

Recommended settings:

• Sampling method: Euler a

• Start with no negative prompt. Sample images were generated without negative prompt.

• CFG: 4-5

• Use ADetailer extension to enhance facial details: https://github.com/Bing-su/adetailer

推荐设置：

• 采样方法：Euler a

• 先尝试不使用负面提示词。示例图片都没有使用负面提示词。

• CFG: 4-5

• 使用 ADetailer 扩展来增强面部细节：https://github.com/Bing-su/adetailer

Change notes:

v3.0: Now supports dark images

v2.0: Updated training strategy improves all areas, including but not limited to: hands, feet, background, styles

v1.1: Skin texture improvements

v1.0: Initial release