andrey-okhotin/star-shaped
Official PyTorch implementation for the paper Star-Shaped Denoising Diffusion Probabilistic Models
This project offers a new method to create diverse data like images or text. It takes a description or a dataset as input and generates new, highly realistic examples that go beyond typical Gaussian (bell-curve) patterns. Scientists and machine learning researchers who need to generate data with complex, non-standard distributions will find this useful for tasks like modeling complex phenomena or artistic generation.
No commits in the last 6 months.
Use this if you need to generate high-quality data that adheres to specific non-Gaussian distributions (like Beta, Dirichlet, or von Mises-Fisher) for specialized tasks.
Not ideal if you primarily work with standard image generation or only need basic, Gaussian-distributed data, as simpler methods may suffice.
Stars
26
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Dec 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/andrey-okhotin/star-shaped"
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.