VinAIResearch/DiMSUM

DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation (NeurIPS 2024)

37
/ 100
Emerging

DiMSUM is a tool for researchers and practitioners in generative AI who need to create high-quality images. It takes raw image data and generates new, highly realistic images. This is for professionals like AI researchers, computer vision engineers, and content creators working with synthetic media.

No commits in the last 6 months.

Use this if you need to generate high-quality, realistic images for datasets like CelebA HQ, LSUN Church, or ImageNet-1K, and prioritize fast training convergence and state-of-the-art results.

Not ideal if you are looking for a simple, out-of-the-box image generation tool without diving into model training and evaluation.

generative-AI image-synthesis computer-vision AI-research deep-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

43

Forks

6

Language

Python

License

BSD-3-Clause

Last pushed

Feb 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/VinAIResearch/DiMSUM"

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