daspartho/MagicMix

Implementation of MagicMix: Semantic Mixing with Diffusion Models paper

29
/ 100
Experimental

This tool helps graphic designers, marketers, and artists create unique hybrid images by blending concepts. You provide an input image to define the spatial layout and a text prompt to define the new content. The output is a new image that semantically mixes both, like turning a telephone into a bed while keeping its original form.

No commits in the last 6 months.

Use this if you need to visually merge the structure of one image with the stylistic or conceptual elements of another, guided by a text description.

Not ideal if you need precise control over pixel-level editing or want to generate completely new images from scratch without a layout reference.

graphic-design digital-art image-manipulation creative-asset-generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

32

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 22, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/daspartho/MagicMix"

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