Skip to content

text-to-pose

Turn a text description into a pose and then an image

Visit official site

What text-to-pose is

The project is described as research that turns a text description into a human pose and then generates an image from that pose.

What you can do with it

  • Convert text into human poses with a Transformer
  • Generate images from poses with diffusion models

Getting started

  • Clone or download the code from the GitHub page
  • Read the README, install dependencies and run training or testing

Pros & cons

✓ What we like

  • Training code and pretrained models are provided
  • A dataset with COCO-2017 annotations is included

! What to watch out for

  • The work is described as a research project
  • Image output follows the generated pose

FAQ

What is the paper basis?

The material cites a paper at the NeurIPS 2024 Workshop.

What is provided for developers?

The material lists training code, pretrained models, a dataset and documentation.

Last reviewed: 2026-11-15

More AI image generation tools

View all →

How we review