wangkai930418/DPL

[NeurIPS 2023] Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing

24
/ 100
Experimental

This tool helps visual artists, graphic designers, or marketers refine existing images by editing them based on text descriptions. You provide an image and a text prompt (like "change the car to red"), and it generates a modified image reflecting your textual instructions. It's designed for anyone who needs precise control over image elements through text-based editing.

111 stars. No commits in the last 6 months.

Use this if you need to perform targeted, text-guided edits on specific objects or regions within an image, such as changing colors or adding details, without affecting other parts of the image.

Not ideal if your image already looks good, as the core method is designed to fix issues related to cross-attention during the editing process, or if you need to ensure perfect editing quality every time.

image-editing visual-content-creation graphic-design digital-art visual-marketing
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

111

Forks

5

Language

Python

License

Last pushed

May 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/wangkai930418/DPL"

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