HKUST-LongGroup/Coarse-guided-Gen

[arXiv 2026] Official PyTorch Repository for "Coarse-Guided Visual Generation via Weighted h-Transform Sampling"

34
/ 100
Emerging

This tool helps creative professionals and researchers enhance visual media. By providing a rough sketch or low-quality image/video, you can generate a refined, high-quality version. It takes a 'coarse' visual input and produces a 'fine' output, suitable for tasks like image restoration or editing. This is ideal for designers, video editors, or scientists working with visual data.

Use this if you need to create high-quality images or videos from an initial, less-detailed visual input, for tasks like upscaling or guided content generation.

Not ideal if you need to generate visuals from scratch without any initial guiding image or video.

image-restoration video-enhancement visual-editing digital-art media-production
No License No Package No Dependents
Maintenance 13 / 25
Adoption 7 / 25
Maturity 3 / 25
Community 11 / 25

How are scores calculated?

Stars

35

Forks

4

Language

Python

License

Last pushed

Mar 16, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/HKUST-LongGroup/Coarse-guided-Gen"

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