ApexGen-X/MergeVQ

[CVPR'25] MergeVQ: A Unified Framework for Visual Generation and Representation with Token Merging and Quantization

33
/ 100
Emerging

This project offers a new way to create and understand images using a unified system. It takes in existing images and processes them to generate new ones or extract key visual information, making image generation faster and more efficient. This is ideal for researchers and developers working on advanced image synthesis and analysis.

No commits in the last 6 months.

Use this if you need to both generate high-quality images and learn meaningful representations from visual data, especially for academic research in computer vision.

Not ideal if you are looking for an off-the-shelf application for immediate use, as this is a research framework requiring technical expertise for implementation.

image-generation visual-representation-learning computer-vision-research self-supervised-learning deep-learning-models
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

47

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Jul 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ApexGen-X/MergeVQ"

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