As a brand new SDXL model, there are three differences between HelloWorld and traditional SD1.5 models:
Unlike SD1.5 base models, which typically do not include trigger words, please remember to use the trigger word "leogirl" when using HelloWorld 1.0. This ensures that the SDXL model triggers the training set effect more stably.
The HelloWorld model supports direct output at a resolution of 1024*1024 pixels, eliminating the need for high-resolution magnification. The quality of close-up portrait directly output is not inferior to the SD1.5 version, but there are still flaws when outputting distant portraits directly. Therefore, it is suggested to use ADetailer plugin, which can effectively correct the problems of distant faces.
SDXL now allows for easier output using simple natural language prompts. It is recommended to try more natural language prompts, which will result in better outcomes when outputting AI realistic photos.
After multiple rounds of testing, the suggested drawing parameter settings are:
Steps ≥ 25
Sampler: DPM++ 2M Karras
CFG scale: 10
Size ≥ 1024x1024
ADetailer: open
作为全新的SDXL模型，HelloWorld在使用时有三点与传统SD1.5模型的不同：
HelloWorld 1.0模型使用必备的触发词是leogirl，除此以外，建议同时添加realistic和looking at viewer两个正向提示词。建议使用的负面提示词是：bad eyes, incorrect hands, worst teeth, abnormal anatomy, wrong lips, illustration, cartoon, painting。
HelloWorld模型支持1024*1024分辨率直接出图，不需要高分辨率放大，目前在近景人像直出质感上不输于SD1.5版本，但直出远景人像时仍存在瑕疵，因此建议搭配ADetailer插件使用，可以很好地修正远景人脸问题。
SDXL现在可以使用更简单的自然语言提示词进行出图，建议多多尝试自然语言提示词，输出AI写实照片时会有更好的效果。
经过多轮测试，建议的绘图参数设置包括：
Steps ≥ 25
Sampler: DPM++ 2M Karras
CFG scale: 10
Size ≥ 1024x1024
ADetailer: open
