mv-lab/InstructIR

[ECCV 2024] InstructIR: High-Quality Image Restoration Following Human Instructions https://huggingface.co/spaces/marcosv/InstructIR

40
/ 100
Emerging

InstructIR helps photographers, graphic designers, and content creators improve their images by following natural language instructions. You input a degraded image and a text prompt describing the desired restoration (e.g., "remove the noise," "make it brighter"), and it outputs a high-quality, enhanced version of your image. This tool allows non-technical users to achieve professional-level image restoration.

710 stars. No commits in the last 6 months.

Use this if you have images suffering from common issues like blur, rain, haze, noise, or poor lighting and want to fix them with simple text commands.

Not ideal if you need to perform highly specific, artistic manipulations beyond standard restoration tasks or require pixel-level manual editing control.

photo-editing image-enhancement digital-photography graphic-design content-creation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

710

Forks

44

Language

Jupyter Notebook

License

MIT

Last pushed

Sep 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/mv-lab/InstructIR"

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