czg1225/CoDe

[CVPR 2025] CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient

34
/ 100
Emerging

This project helps machine learning engineers and researchers accelerate their image generation workflows. By intelligently combining large and small models, it takes in parameters for image generation and outputs high-quality images much faster, while using less memory. This is ideal for those working on visual auto-regressive models who need to generate 256x256 resolution images efficiently.

108 stars. No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher focused on visual auto-regressive modeling and need to generate 256x256 images faster and with less GPU memory.

Not ideal if you are working with other image resolutions, need to train image generation models from scratch, or are not familiar with visual auto-regressive frameworks.

image-generation computational-efficiency generative-AI deep-learning-research computer-vision
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

108

Forks

5

Language

Python

License

MIT

Last pushed

Sep 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/czg1225/CoDe"

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