We provide 4 models of varying size. Sapiens-0.3B, Sapiens-0.6B, Sapiens-1B, Sapiens-2B. In general, performance improves with increasing the model size.
Best for general in-the-wild scenarios with body keypoints only, adhering to the COCO keypoint format.
Coming Soon!
Offers second-best generalization with body, face, hands, and feet keypoints, following the COCO-WholeBody keypoint format.
Coming Soon!
The highest number of keypoints predictor. Detailed 274 face keypoints. Following the Sociopticon keypoint format.
| Model | Checkpoint Path |
|---|---|
| Sapiens-0.3B | Coming Soon! |
| Sapiens-0.6B | Coming Soon! |
| Sapiens-1B | $SAPIENS_CHECKPOINT_ROOT/pose/checkpoints/sapiens_1b/sapiens_1b_goliath_coco_wholebody_mpii_crowdpose_aic_best_goliath_AP_640.pth |
| Sapiens-2B | Coming Soon! |
Navigate to the script directory and launch the inference scripts for your desired keypoint configuration.
- Navigate to your script directory:
cd $SAPIENS_ROOT/pose/scripts/demo/local
- For 17 keypoints estimation (uncomment your model config line for inference):
./keypoints17.sh
- For 133 keypoints estimation (uncomment your model config line for inference):
./keypoints133.sh
- For 308 keypoints estimation (uncomment your model config line for inference, we recommend using face crops for better results!):
./keypoints308.sh
Define INPUT for your image directory and OUTPUT for results. Visualization and keypoints in JSON format are saved to OUTPUT. Customize LINE_THICKNESS, RADIUS, and KPT_THRES as needed. Adjust JOBS_PER_GPU, TOTAL_GPUS and VALID_GPU_IDS for multi-GPU configurations.
Generate OpenPose skeletons on a black background, compatible with ControlNet.
- Navigate to your script directory:
cd $SAPIENS_ROOT/pose/scripts/demo/local
- For 17 keypoints estimation (uncomment your model config line for inference):
./keypoints17_openpose.sh
- For 133 keypoints estimation (uncomment your model config line for inference):
./keypoints133_openpose.sh
Customization options as mentioned above are applicable here as well.
