perceivelab/trf-sg2im

Official PyTorch implementation of the paper Transformer-Based Image Generation from Scene Graphs https://arxiv.org/abs/2303.04634

34
/ 100
Emerging

This project helps researchers and developers working with generative AI to create realistic images based on structured scene descriptions. You provide a scene graph (a JSON file detailing objects and their relationships), and it outputs a high-quality image that visually represents that scene. This is useful for anyone exploring advanced image generation and synthetic data creation.

No commits in the last 6 months.

Use this if you need to generate diverse and high-quality images with precise control over object composition and relationships within the scene.

Not ideal if you need a simple image generator that doesn't require structured scene graph inputs or if your primary goal is rapid, less controlled image synthesis.

generative-ai computer-vision synthetic-data image-synthesis AI-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

19

Forks

3

Language

Python

License

GPL-3.0

Last pushed

Jan 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/perceivelab/trf-sg2im"

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