Computer vision

ViTPose

A simple, accurate model for human pose estimation via keypoints. ViTPose++ handles human, animal and whole-body poses; built into the Transformers library.

Developer
University of Sydney and JD Explore Academy, Australia / China
First release
May 2022
Latest release
Jan 2025
Sizes
33M – about 1B
License
Commercial use allowedApache 2.0
Running
On your own serverAlso runs without a GPU
Industries
Manufacturing and logistics, Media and production, Healthcare
Deploy on your server Hugging Face GitHub

What it does

  • Body keypoints in photos and video
  • Motion analysis in sports and rehabilitation
  • Monitoring work postures and safety practices
  • Preparing a skeleton for animation

Where it is used

Sports and fitnessManufacturing and occupational safetyVideo production

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. ViTPose / ViTPose++ в Transformers
  2. ViTPose++
  3. ViTPose

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can ViTPose be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does ViTPose need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does ViTPose support Russian?

Language does not matter for this model: it does not work with text.

Where can I download ViTPose and what does it cost?

The ViTPose weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Computer visionSapiensMeta · USACommercial use with conditions

Meta's models for analyzing people in photos: pose keypoints, body part segmentation, normals and depth. Sapiens2 was trained at high resolution and adds human matting.

DetailsComputer visionYOLO (Ultralytics)Ultralytics · USACommercial use with conditions

The most widely used real-time object detector: finds and marks items in video even on modest hardware. YOLOv5 came out back in 2020; the catalog starts from YOLOv8.

Details

Source: huggingface.co/usyd-community/vitpose-plus-huge. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.