DAMO-NLP-SG/DiGIT

[NeurIPS 2024] Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective

28
/ 100
Experimental

This project offers an advanced method for generating realistic and coherent images from scratch, or for better understanding the content of existing images. It takes raw image data and processes it to produce high-quality synthetic images or to extract meaningful insights about image features. This tool is ideal for researchers and practitioners in computer vision, generative AI, and digital media who need to create new images or improve image analysis capabilities.

No commits in the last 6 months.

Use this if you need to generate high-fidelity images for research or applications, or if you want to enhance the accuracy of image classification and understanding tasks.

Not ideal if your primary need is for video generation, 3D model creation, or if you require extremely low computational overhead for real-time applications on limited hardware.

image-generation computer-vision generative-ai image-understanding deep-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 3 / 25

How are scores calculated?

Stars

79

Forks

1

Language

Python

License

MIT

Last pushed

Oct 31, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/DAMO-NLP-SG/DiGIT"

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