独创的三步生图法，目的是解决lora、画师tag等对模型生图能力固化的现象，通过多步生成赋予最大的生成操作空间。
这个工作流逻辑简单易懂，包含lora、放大、面部修复，一站式生图。
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Anzhc Face seg 640 v4 y11n.pt · Anzhc/Anzhcs_YOLOs at main
眼部检测模型下载地址Anzhc Eyes -seg-hd.pt · Anzhc/Anzhcs_YOLOs at main
4x-UltraSharpV2_Lite模型下载地址https://huggingface.co/Kim2091/UltraSharpV2/tree/main
线条ControlNet下载地址mistoLine_rank256.safetensors · TheMistoAI/MistoLine at 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 Anzhc Face seg 640 v4 y11n.pt · Anzhc/Anzhcs_YOLOs at main
Eye detection model download address Anzhc Eyes -seg-hd.pt · Anzhc/Anzhcs_YOLOs at main
4 x - UltraSharpV2_Lite model download address https://huggingface.co/Kim2091/UltraSharpV2/tree/main
ControlNet Line model download address mistoLine_rank256.safetensors · TheMistoAI/MistoLine at 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.
FAQ
Comments (8)
大佬，请问comfy好学吗？
好b（￣▽￣）d 实在不会还可以直接复制其他人的工作流
收到！
大佬请问一下您的高清修复模型能否给个链接
这个随意都可以