![\"\"](\"https:\/\/jurn.link\/dazposer\/wp-content\/uploads\/2025\/07\/workingopen.jpg\")
<\/a><\/p>\n1.<\/strong> Use your existing ComfyUI or, if new, then try the ComfyUI Windows portable<\/a>. For the Portable, cut the entire custom_nodes<\/em> folder and place the more immediately useful individual custom_nodes<\/em> folders back one-by-one, if ComfyUI fails to load all its UI elements on startup. I found that one of the custom_nodes was stopping the full UI from loading.<\/p>\n 2.<\/strong> Into your ComfyUI you install ComfyUI’s ControlNet Auxiliary Preprocessors<\/a> packages, which come in a big bundle… and one of these is for openpose processing.<\/p>\n 3.<\/strong> Into your ComfyUI you also install DWPose as ComfyUI-Dwpose-Tensorrt<\/a> to speed things up. You’re on Windows and NVIDIA, I assume.<\/p>\n 4.<\/strong> Download two required Torch files dw-ll_ucoco_384_bs5.torchscript.pt<\/a> and yolox_l.onnx<\/a>. About 500Mb in total, and they’re open on HuggingFace. There are two folders to manually put these in, for me…<\/p>\n C:\\ComfyUI_Windows_portable\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\ckpts\\yzd-v\\DWPose\\<\/em><\/p>\n C:\\ComfyUI_Windows_portable\\ComfyUI\\custom_nodes\\comfyui_controlnet_aux\\ckpts\\hr16\\DWPose-TorchScript-BatchSize5\\<\/em><\/p>\n I was told to put the files in the first yzd-v<\/em> folder and then the workflow gave me a ‘not found, download from Huggingface’ error. However, I then also tried copying the same files to the second hr16<\/em> folder and… the Openpose workflow worked.<\/p>\n 5.<\/strong> My simple Openpose workflow for Comfy, working. Just drop an image in and ‘Run’. Should take about five seconds to produce an Openpose image.<\/p>\n As you can see, you can switch off face and\/or hands if they’re not required.<\/p>\n You then save out this special image, and drop it into a Controlnet workflow which has an openpose model (here for SDXL<\/a> models) linked to it…<\/p>\n<\/a><\/p>\n