X1716/IQA-Adapter

[ICCV 2025 Highlight] Code for the paper "IQA-Adapter: Exploring Knowledge Transfer from Image Quality Assessment to Diffusion-based Generative Models"

16
/ 100
Experimental

This tool helps creative professionals or researchers working with AI image generation by letting them control the visual quality and aesthetic appeal of the generated images. You provide an image prompt or an existing image, and it outputs new images that meet specific quality or aesthetic standards, like clarity, composition, or color vibrancy. It's ideal for anyone who needs fine-grained control over the visual characteristics of AI-generated content beyond just its subject matter.

No commits in the last 6 months.

Use this if you need to create AI-generated images that adhere to specific benchmarks for visual quality or aesthetic preferences, ensuring the output meets high standards without extensive manual editing.

Not ideal if you are only interested in generating diverse images without specific quality or aesthetic constraints, or if you need a simple, out-of-the-box solution without any technical setup.

AI-art-generation digital-content-creation computational-photography visual-media-design image-processing
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

19

Forks

Language

Jupyter Notebook

License

Last pushed

Sep 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/X1716/IQA-Adapter"

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