kohinoor23/How-Diffusion-Models-Work

Notes from How Diffusion Models Work by DeepLearning.ai

34
/ 100
Emerging

These notes explain how to create new images from existing ones using diffusion models. You start with a collection of images, like character sprites for a video game, and the model learns to generate many more similar, high-quality images. This is for game developers, graphic designers, or artists looking to expand their creative asset libraries.

No commits in the last 6 months.

Use this if you need to understand the underlying mechanics of how diffusion models learn to generate new images from scratch, based on a dataset of existing images.

Not ideal if you are looking for an off-the-shelf tool to generate images without understanding the technical details of the model's architecture or training process.

game-art-generation digital-illustration image-synthesis asset-creation generative-design
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

27

Forks

20

Language

Jupyter Notebook

License

Last pushed

Dec 04, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/kohinoor23/How-Diffusion-Models-Work"

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