ali-vilab/IDEA-Bench
Official repository of IDEA-Bench
This project helps professional designers and graphic artists assess how well AI image generation models perform on real-world design tasks. It takes text prompts or existing images as input and evaluates the generated visuals based on criteria like aesthetic quality and contextual relevance, providing objective scores that show how close AI-generated designs are to professional standards.
No commits in the last 6 months.
Use this if you are a professional designer, graphic artist, or researcher who needs to rigorously evaluate and compare the performance of different AI image generation models for complex design workflows.
Not ideal if you are looking for an image generation tool to create designs directly, rather than a benchmark for evaluating AI models.
Stars
39
Forks
2
Language
Python
License
—
Category
Last pushed
Jan 24, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ali-vilab/IDEA-Bench"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Vchitect/VBench
[CVPR2024 Highlight] VBench - We Evaluate Video Generation
VectorSpaceLab/OmniGen
OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340
EndlessSora/focal-frequency-loss
[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis
JIA-Lab-research/DreamOmni2
This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing...
SkyworkAI/UniPic
Open-source SOTA multi-image editing model