hila-chefer/Conceptor

Official implementation of the paper The Hidden Language of Diffusion Models

17
/ 100
Experimental

This project helps AI researchers and practitioners understand how text-to-image diffusion models interpret concepts. You input a text concept (like "a president") or a specific image, and it outputs a breakdown of that concept into simple, human-understandable textual elements. This allows you to see the surprising visual connections and biases within the model's internal representations.

No commits in the last 6 months.

Use this if you need to explain, debug, or deeply understand the latent space and concept representation within your text-to-image diffusion models.

Not ideal if you are looking to generate images directly, fine-tune models, or evaluate image quality.

AI explainability Generative AI research Model interpretation Diffusion model analysis Concept visualization
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

78

Forks

Language

License

Last pushed

Jan 24, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/hila-chefer/Conceptor"

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