aimagelab/MAD

Official PyTorch implementation for "Merging and Splitting Diffusion Paths for Semantically Coherent Panoramas", presenting the Merge-Attend-Diffuse operator (ECCV24)

21
/ 100
Experimental

This tool helps you create ultra-wide, immersive panoramic images from simple text descriptions. You provide a prompt describing the scene you want, and it generates a sprawling image that feels naturally connected and cohesive across its entire width, unlike standard image generators. It's for designers, marketers, or anyone needing highly specific, expansive visuals without complex photo editing.

No commits in the last 6 months.

Use this if you need to generate unique, semantically coherent panoramic images from text prompts for creative projects, marketing materials, or visual content creation.

Not ideal if you need to generate standard-sized images, edit existing photos, or require precise photorealistic output of real-world scenes.

generative-art visual-content-creation digital-design marketing-graphics text-to-image
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

14

Forks

1

Language

Python

License

Last pushed

Jul 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/aimagelab/MAD"

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