SDPose-Wholebody is an open source human pose estimation model that uses diffusion priors from Stable Diffusion to robustly detect 133 wholebody keypoints in images. It is intended for computer vision researchers and developers seeking advanced pose estimation capabilities, especially in challenging or out-of-domain scenarios.
SDPose Wholebody is an Other AI product. Accurately detecting and estimating human body keypoints in images, including out-of-distribution scenarios. It is built as an open-source project for computer vision researchers and developers. SDPose Wholebody is open source under the MIT license. SDPose Wholebody is available on the command line.
Behind SDPose Wholebody is Kyps, and the product first shipped in 2025. Development happens publicly on GitHub with 154 stars and 1 commits in the last 90 days. Key capabilities include pose estimation, wholebody keypoints, and diffusion priors.
Latest indexed changes and source events
Kyps/SDPose-Wholebody verified by the PulseGate indexer
Other apps tracked under the same category.
