CompVis/stable-diffusion

A latent text-to-image diffusion model

Jupyter Notebook73K stars11K forks+36 today

What it does

Stable Diffusion is a text-to-image generation model that creates high-resolution images from textual descriptions, leveraging advanced machine learning techniques to produce visually compelling outputs.

Star history

Not enough history yet — 1 day(s) recorded. The daily snapshot builds this up.

Tracking

Last trending: 2026-04-25

Creator kit

Hook

Transform your imagination into stunning visuals with Stable Diffusion - the ultimate text-to-image AI model!

Content angles

Create tutorials on how to use Stable Diffusion for generating art and designs.
Analyze the ethical implications of using such powerful image generation tools.
Develop a comparison review between Stable Diffusion and other leading text-to-image models.

Who should care

AI researchers, artists, developers interested in machine learning applications