FareedKhan-dev/create-stable-diffusion-from-scratch
Implemented a stable diffusion architecture using PyTorch.
This project helps machine learning engineers understand and implement the core components of a Stable Diffusion model from the ground up. It takes fundamental machine learning concepts and demonstrates how to build a small-scale image generation model using the MNIST dataset. The end result is a working Stable Diffusion model that can generate simple images, providing hands-on experience for those looking to deepen their knowledge of diffusion models.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher who wants to learn the inner workings of Stable Diffusion by building a simplified version from scratch.
Not ideal if you are looking for a production-ready, high-quality image generation tool for complex creative tasks or large-scale data.
Stars
83
Forks
16
Language
Jupyter Notebook
License
—
Category
Last pushed
Jan 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/FareedKhan-dev/create-stable-diffusion-from-scratch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
siliconflow/onediff
OneDiff: An out-of-the-box acceleration library for diffusion models.
wooyeolbaek/attention-map-diffusers
🚀 Cross attention map tools for huggingface/diffusers
jina-ai/discoart
🪩 Create Disco Diffusion artworks in one line
chengzeyi/stable-fast
https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace...
hkproj/pytorch-stable-diffusion
Stable Diffusion implemented from scratch in PyTorch