aju22/DDPM
This is an easy to understand, simplified, broken-down implementation of Diffusion Models written in PyTorch. The architecture is borrowed from the paper "Denoising Diffusion Probabilistic Models"
This project helps generate new, high-quality images based on a collection of existing images. It takes your dataset of images as input and can then produce entirely new images that resemble your original data. This is useful for researchers and artists looking to create novel visual content or expand datasets.
No commits in the last 6 months.
Use this if you need to generate high-quality, realistic images from scratch, based on patterns learned from a training set.
Not ideal if you need to manipulate existing images, classify them, or perform tasks other than generating new ones.
Stars
27
Forks
2
Language
Jupyter Notebook
License
—
Category
Last pushed
Aug 18, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/aju22/DDPM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
bghira/SimpleTuner
A general fine-tuning kit geared toward image/video/audio diffusion models.
mcmonkeyprojects/SwarmUI
SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an...
nateraw/stable-diffusion-videos
Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
TheDesignFounder/DreamLayer
Benchmark diffusion models faster. Automate evals, seeds, and metrics for reproducible results.