chen-hao-chao/dlsm

[ICLR 2022] Denoising Likelihood Score Matching for Conditional Score-based Data Generation

33
/ 100
Emerging

This project provides the tools to generate new, high-quality synthetic images based on existing image datasets. You can input a collection of images, specify conditions or categories, and receive a set of newly created images that resemble the originals but are entirely unique. This is ideal for researchers, data scientists, or machine learning engineers working on image synthesis and conditional data generation tasks.

No commits in the last 6 months.

Use this if you need to create diverse, realistic synthetic images conditioned on specific attributes or categories from an existing dataset for research or augmentation.

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

image-synthesis data-augmentation generative-modeling synthetic-data computer-vision-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

11

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Jan 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/chen-hao-chao/dlsm"

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