boomb0om/text2image-benchmark
Benchmark for generative image models
This project helps researchers and developers evaluate the quality of text-to-image models. It takes a set of generated images and their corresponding text descriptions, or directly uses a text-to-image model, and outputs standardized metrics like FID and CLIP-score. This is primarily for machine learning engineers, AI researchers, and data scientists working with generative AI.
108 stars. No commits in the last 6 months.
Use this if you need to objectively compare the performance and image generation quality of different text-to-image AI models using established metrics.
Not ideal if you are an end-user simply looking to generate images and do not need to evaluate model performance scientifically.
Stars
108
Forks
6
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Sep 09, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/boomb0om/text2image-benchmark"
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