KAIST-Visual-AI-Group/SyncDiffusion

[NeurIPS 2023] Official implementation of SyncDiffusion

36
/ 100
Emerging

This tool helps artists, designers, and marketers create consistent and expansive visual content, such as panoramas or montages, from text descriptions. You provide a text prompt describing the desired scene, and it generates multiple images that seamlessly blend together to form a coherent, large-scale visual. It's ideal for anyone needing to generate wide, unified images without visible seams or mismatched scenes.

168 stars. No commits in the last 6 months.

Use this if you need to generate high-quality, wide-format images or montages from a text prompt where visual consistency and seamless blending between generated sections are critical.

Not ideal if you're looking for a tool to simply stitch pre-existing photos together without generating new content or if you don't require text-to-image capabilities.

digital-art-generation visual-content-creation panoramic-image-synthesis design-asset-creation marketing-visuals
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

168

Forks

10

Language

Jupyter Notebook

License

MIT

Last pushed

Apr 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/KAIST-Visual-AI-Group/SyncDiffusion"

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