pose-estimation AI Models

🤖 Model

fire/v-sekai.mediapipe-labeler

Label facial blendshapes and pose keypoints from images or videos. Detect up to 1–100 people and return per-frame JSON a...

pose-estimation • face-detection • facial-blendshapes • 218 runs

🤖 Model 🖼️

hautechai/yolo11x-pose-image

Estimate human poses in images and output an image annotated with keypoints and skeletons. Uses Ultralytics YOLOv11 Pose...

🖼️ • pose-estimation • image-object-detection • 72 runs

🤖 Model

aiunivers/openpose

Estimate human pose from an input image and output an OpenPose-style pose map image. Optionally include facial landmarks...

pose-estimation • depth-estimation • openpose • 433 runs

🤖 Model

hautechai/yolo11x-pose

Estimate human body pose from an input image, returning 2D keypoint coordinates for each detected person. Leverage YOLO-...

pose-estimation • 130 runs

🤖 Model 🖼️ → 🖼️

sai88uk/openpose-skeleton-detector-v2

Detect human pose skeletons from an image and output a colored OpenPose-style visualization. Extract 25 body keypoints,...

🖼️ → 🖼️ • pose-estimation • image-to-image • 35 runs

🤖 Model 🎥

lucataco/vid2densepose

Convert videos to DensePose representations. Takes a video as input and outputs a video visualizing per-frame DensePose...

🎥 • video-to-video • pose-estimation • 6.3K runs

🤖 Model 🎥

e1100x/openpose

Estimate human pose from images or videos and return a visualized 2D skeleton (OpenPose-style) as an image or video. Ren...

🎥 • pose-estimation • video-to-video • 565 runs

🤖 Model 🎥

lucataco/vid2openpose

Extract human pose from a video and output an OpenPose-style skeleton video. Provide a video as input and receive a vide...

🎥 • pose-estimation • video-to-video • openpose • 2.0K runs

🤖 Model 🖼️

adirik/lightweight-openpose

Estimate 2D poses of multiple people in an image using a lightweight version of OpenPose. Outputs include 18 keypoints p...

🖼️ • pose-estimation • multi-person • 2d-pose • 1.6K runs

🤖 Model 🖼️

chigozienri/densepose

Generate DensePose UV and segmentation maps from an image or video to create driving poses for MagicAnimate and other mo...

🖼️ • pose-estimation • image-segmentation • 1.7K runs

🤖 Model

vegetebird/human-pose-estimation

Estimate 2D and 3D human pose from a single-person image or short video. Return a visualization video with skeletal over...

pose-estimation • keypoint-extraction • 225 runs

🤖 Model

fofr/controlnet-preprocessors

Generate ControlNet conditioning maps from an input image. Run multiple preprocessors simultaneously and return images f...

controlnet-preprocessor • pose-estimation • depth-estimation • 42.5K runs

🤖 Model 🖼️ → 🎥

douwantech/musepose

Generates videos of virtual humans by transferring poses from an input video to a reference person image. Takes a refere...

🖼️ → 🎥 • image-to-video • pose-estimation • video-consistent-character-generation • 1.0K runs

🤖 Model 📝 → 🖼️

prompthunt/cog-sdxl-controlnet-inference

Generates images from text prompts using Stable Diffusion XL with ControlNet conditioning. Supports pose-guided generati...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 325 runs