ashual/scene_generation

A PyTorch implementation of the paper: Specifying Object Attributes and Relations in Interactive Scene Generation

44
/ 100
Emerging

This project helps graphic designers or content creators generate complex images by specifying objects and their relationships. You provide a description of objects, their attributes (like color or texture), and how they relate to each other (e.g., 'a red car next to a blue house'). The system then generates a corresponding visual scene. This is ideal for anyone who needs to quickly prototype visual concepts without manual drawing.

192 stars. No commits in the last 6 months.

Use this if you need to rapidly create diverse visual scenes based on textual descriptions of objects and their arrangements.

Not ideal if you require photorealistic images with fine-grained artistic control over every detail.

graphic-design content-creation visual-prototyping concept-art scene-composition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

192

Forks

30

Language

Python

License

Apache-2.0

Category

gan-based-t2i

Last pushed

Oct 03, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ashual/scene_generation"

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