TIGER-AI-Lab/ImagenHub

A one-stop library to standardize the inference and evaluation of all the conditional image generation models. [ICLR 2024]

46
/ 100
Emerging

Provides unified inference across 50+ conditional image generation models (text-to-image, image editing, inpainting, etc.) with curated evaluation datasets for 7 tasks and standardized metrics including LPIPS, CLIP-based scores, and human evaluation protocols (semantic consistency, perceptual quality). The library supports popular frameworks like Stable Diffusion, SDXL, and DALL-E through a modular architecture that abstracts model-specific implementations, enabling fair benchmarking and reproducible comparisons via YAML configuration files.

178 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

178

Forks

19

Language

Python

License

MIT

Last pushed

Dec 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/TIGER-AI-Lab/ImagenHub"

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