🚀Edit& Run it online (RunningHub):

https://www.runninghub.ai/post/1863915071544967170/?utm_source=openar

RunningHub – Highly Reliable Cloud-Based ComfyUI, Edit and Run Workflows Online, no local installation required. Powered by RTX 4090 GPUs for faster performance and fully error-free node operation.

----------------------------------------------------------

🚀 在线编辑运行（RunningHub):

https://www.runninghub.cn/post/1863422879802261506/?utm_source=openart

【RunningHub - 超高可用性云端ComfyUI，在线编辑运行工作流，标配RTX4090带来更快运行速度，节点全不报红】

----------------------------------------------------------

Workflow Description

Open the workflow, on the far left of the screen, first upload an image, generate a unified character through the controlnet skeleton model, then split the 4 pose images, and then use SegmentAnythingUltra_V2 for matting and overlay processing. Then use the flux1-redux-dev model to transfer the image style, and then use the flux1-fill-dev model to redraw the mask area. Finally, give it to the sampler to generate the effect map.

This workflow has many nodes, so it is divided into two parts. At this stage, it is multi-pose model clothing migration to ensure consistency. Now the picture is a bit blurry, it is recommended to find a high-definition repair portrait workflow to run.

Recommended online runnable workflow URL:

https://www.runninghub.ai/post/1880594839137601516

https://www.runninghub.cn/post/1806603389481996289

----------------------------------------------------------

工作流内容介绍

打开工作流，在画面最左侧，首先上传1张图像，通过controlnet 骨骼模型生成统一性的人物角色，其次把4张pose的图像拆分，再用SegmentAnythingUltra_V2进行抠像叠加处理。然后通过flux1-redux-dev模型对图像进行风格迁移，再用flux1-fill-dev模型对mask区域进行重绘。最后给到采样器生成效果图。

该工作流，节点较多，所以分成2部分，现阶段是多pose模特服装迁移，保证了一致性。现在画面有些模糊，推荐找个高清修复的人像工作流运行。

推荐在线可运行工作流网址：

https://www.runninghub.ai/post/1880594839137601516

https://www.runninghub.cn/post/1806603389481996289

----------------------------------------------------------

RunningHub：Join Us to Claim Free Perks