masa-ue/SVDD-image

Derivative-Free, Training-Free, Guidance in Diffusion Models

23
/ 100
Experimental

This tool helps researchers and designers generate images that are optimized for specific qualities, such as compressibility or aesthetic appeal, without needing extensive training or fine-tuning of the underlying models. You provide a prompt and specify the desired quality, and the system produces new images that best meet that criterion. It's ideal for anyone working with image generation who needs to quickly create high-quality, targeted visual content.

No commits in the last 6 months.

Use this if you need to generate images optimized for specific qualities like compressibility or aesthetic score using diffusion models, without the time and computational cost of model training or fine-tuning.

Not ideal if you are looking to generate biological sequences or if your primary goal is general-purpose image generation without specific optimization objectives.

generative-AI-research computational-creativity image-optimization content-creation AI-art
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

16

Forks

2

Language

Python

License

Last pushed

Sep 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/masa-ue/SVDD-image"

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