horenbergerb/BernoulliDiffusion
Simple diffusion implementation for binary-valued data using a Bernoulli distribution instead of a Gaussian.
This tool helps machine learning engineers or researchers generate new, synthetic binary data that looks just like their existing datasets. You provide it with a collection of binary sequences (composed of 1s and 0s), and it learns the patterns to produce an unlimited number of new sequences with similar characteristics. It's designed for those working with fixed-length binary data.
No commits in the last 6 months.
Use this if you need to create more binary data samples that mimic the distribution of an existing binary dataset, for tasks like data augmentation or generating synthetic examples.
Not ideal if your data is not binary (e.g., continuous numbers, images, or text) or if you need to generate data that varies in length.
Stars
22
Forks
5
Language
Python
License
MIT
Category
Last pushed
Nov 14, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/horenbergerb/BernoulliDiffusion"
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.