chigozienri/densepose 🖼️❓✓ → 🖼️

▶️ 2.0K runs 📅 Dec 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License
image-segmentation pose-estimation

About

Create driving poses for magic-animate

Example Output

Output

Example output

Performance Metrics

13.30s Prediction Time
136.28s Total Time
Input Parameters
input (required) Type: string
Input image or video
model Default: R_50_FPN_s1x
DensePose model. Read about the available models: https://github.com/facebookresearch/detectron2/blob/main/projects/DensePose/doc/DENSEPOSE_IUV.md
overlay Type: booleanDefault: false
Overlay the segmentation on the input image
visualizer Default: FineSegmentation
Visualizer to use
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
/root/.pyenv/versions/3.11.7/lib/python3.11/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3526.)
return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
Version Details
Version ID
e2466793b9a60a3891202f1b93527c5db7bbcd7dbb181c11958b50e25f2d55c3
Version Created
December 7, 2023
Run on Replicate →