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
添加了草图与上色图的对比节点,面部修后前后对比节点。
优化面部修复参数。
Added comparison nodes for sketches and colored images, as well as nodes for comparing before and after facial adjustments.
Optimize the facial restoration parameters.