Kevin-thu/DiffMorpher

Official Code for DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing (CVPR 2024)

43
/ 100
Emerging

This project helps you create smooth, visually coherent transitions between two different images or objects, essentially 'morphing' one into the other. You provide two input images and descriptive text prompts for each, and it generates a video or sequence of frames showing the transformation. This is ideal for artists, animators, or content creators looking to produce dynamic visual effects.

506 stars. No commits in the last 6 months.

Use this if you need to generate a seamless animation that gradually transforms one image into a completely different one, like a person aging or an animal changing species.

Not ideal if you're looking for simple image blending or cross-fading, or if your images are highly dissimilar with no logical transition.

animation visual-effects digital-art creative-content image-manipulation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

506

Forks

53

Language

Python

License

Last pushed

Apr 24, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Kevin-thu/DiffMorpher"

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