YangLing0818/SGDiff

Official implementation for "Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training" https://arxiv.org/abs/2211.11138

36
/ 100
Emerging

This tool generates complex images from descriptive structural annotations. You provide a "scene graph" specifying objects, their attributes (like "red" or "large"), and how they relate to each other (e.g., "person riding a bicycle"). The output is a visual representation of that precise scene. This is ideal for researchers in computer vision or AI who need to create custom image datasets for experiments or model training.

No commits in the last 6 months.

Use this if you need to generate synthetic images with fine-grained control over objects, their properties, and relationships within a scene.

Not ideal if you're looking for a simple text-to-image generator without needing to define explicit object relationships.

computer-vision image-generation synthetic-data AI-research scene-understanding
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

77

Forks

18

Language

Python

License

Last pushed

Dec 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/YangLing0818/SGDiff"

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