MICV-yonsei/DragText

[WACV 2025 ORAL] Official Pytorch Code for DragText: Rethinking Text Embedding in Point-based Image Editing

31
/ 100
Emerging

This tool helps graphic designers, digital artists, and creative professionals precisely manipulate objects within existing images. You provide an image and a text prompt, then 'drag' specific points on the image to new locations. The output is a new image where the object has been moved or reshaped according to your drags, while maintaining visual quality.

No commits in the last 6 months.

Use this if you need to precisely adjust the position or shape of elements in an image using intuitive 'drag-and-drop' controls, rather than complex masking or manual redrawing.

Not ideal if you primarily work with generating entirely new images from text prompts or require advanced compositing and layering capabilities.

digital art image editing graphic design visual content creation photo manipulation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

14

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Jan 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/MICV-yonsei/DragText"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.