Legs apart

Multiple ControlNets

Model-based Pixel Upscale Workflow

Hires fix 只是以较低的分辨率创建图像，将其放大，然后通过 img2img 发送。请注意，在 ComfyUI 中，txt2img 和 img2img 是同一个节点。Txt2Img 是通过将空图像传递到具有最大降噪的采样器节点来实现的。

It is used to create images from another image.

With this workflow you will be able to generate a 3x3 grid with the same character face in 9 different poses and with small expression differences. The workflow will output an upscaled image that can then be split in 9 different square image for LoRA training.

The workflow utilizes ComfyUI and its IP-Adapter V2 to seamlessly swap outfits on images.

上传衣服，上传要换装的模特，即可一键更换服装。

跑游戏素材可用，其他用途不大