ConceptBed/evaluations

[AAAI 2024] ConceptBed Evaluations for Personalized Text-to-Image Diffusion Models

27
/ 100
Experimental

This project offers an evaluation framework for researchers working with personalized text-to-image generative AI models. It helps assess how well these models learn and combine specific visual concepts. You input a collection of images generated by your text-to-image model, and it outputs performance metrics and visualizations showing how accurately your model understood and aligned with the intended concepts.

No commits in the last 6 months.

Use this if you are a researcher or AI practitioner developing or fine-tuning personalized text-to-image diffusion models and need a standardized way to evaluate their ability to learn and compose visual concepts.

Not ideal if you are an end-user simply generating images and not focused on the underlying model's conceptual learning performance.

AI-research generative-AI computer-vision model-evaluation image-synthesis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

25

Forks

1

Language

Python

License

MIT

Last pushed

Jun 01, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ConceptBed/evaluations"

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