这个工作流逻辑比较简单，但是包含lora、放大、修复。
默认模型仅供测试使用。您可以使用任何您喜欢的模型。
面部检测模型下载地址https://github.com/akanametov/yolo-face
眼部检测模型下载地址https://civarchive.com/models/334668/eye-detailersegmentation-adetailer
4x-UltraSharpV2_Lite模型下载地址https://huggingface.co/Kim2091/UltraSharpV2/tree/main
This workflow logic is relatively simple, but it includes lora, amplification, and repair.
The default model is only for testing purposes. You can use any model you like.
Face detection model download address https://github.com/akanametov/yolo-face
Eye detection model download address https://civarchive.com/models/334668/eye-detailersegmentation-adetailer
4 x - UltraSharpV2_Lite model download address https://huggingface.co/Kim2091/UltraSharpV2/tree/main
Description
在v3.0的基础上进一步优化。用现实作画的逻辑构建工作流，分为草稿、上色、放大、细节修复。此工作流还可以解决提示词添加画师tag后构图固化和面部固化的问题。
Further optimized on the basis of v3.0. Build the workflow with the logic of painting in reality, which is divided into draft, coloring, magnification and detail restoration. This workflow can also solve the problems of composition solidification and facial solidification after adding the artist's tag to the prompt words.