Slimy_HMR2_VNCCS
A ComfyUI custom node that converts HMR2 keypoints3d output into Pose JSON format compatible with VNCCS PoseStudio. Detects people in a photo, extracts pose keypoints, and uses HMR2 to infer 3D depth for each joint — automatically generating pose data ready to use in VNCCS PoseStudio. > [!WARNING] > This node requires SlimyHMR2keyPoint3D to be used together.(https://github.com/Slimy-Comfy/SlimyHMR2keyPoint3D) > On the first run of that node, approximately 2.5 GB of model data will be automatically downloaded, which may take a significant amount of time. > Also, you will need to download the model data from a specific site. Please read the instructions about its repositry carefully. > After that, inference runs in approximately 6 seconds. Reads 3D keypoints estimated by HMR2 (a human pose estimation AI) and automatically generates bone rotation values (Euler angles) suited for PoseStudio mannequins. 1. Connect the HMR2 node output (keypointsjson) to the input of this node. 2. Run the node — the conversion result will appear in the text area on screen. 3. Press the Export VNCCS PoseData button to download a Pose JSON file that can be loaded into PoseStudio. | Socket | Description | |---|---| | VNCCSPOSE | Clean Pose JSON for PoseStudio | | debugjson | Full data including debug info (KPf coordinates) | HMR2 keypoints3d (SMPL coordinate system) ↓ fitkptomannequin() fittedKP (stick-figure coordinates normalized to mannequin space) ↓ convertfittedtopose() Pose JSON (bone rotation values for PoseStudio + modelRotation) HMR2 and PoseStudio use different coordinate systems. The con…
Slimy/HMR2 · 1 Eingabe · 0 Parameter · 2 Ausgaben
