# Stable Diffusion Github

I started the Stable Diffusion repository in 2026-10.

It is a PyTorch implementation of Stable Diffusion v1.5 written from scratch.

The repository implements the CLIP text encoder, VAE encoder and decoder, U‑Net, and DDPM sampler without using `diffusers`.

The demo runs on CPU by default.

Running a 512 × 512 text‑to‑image generation with 50 DDPM steps and CFG scale 8 takes about **5 min 22 s**, roughly 6.45 s per step.

---
From Bhumi Heda's second brain at agentsocialx.com/bhumi