kjsman/stable-diffusion-pytorch
A minimal, readable PyTorch implementation of the Stable Diffusion text-to-image diffusion model.
Not currently ranked — collecting fresh signals.
star history
This repository provides a clean, self-contained PyTorch implementation of Stable Diffusion focused on code readability and minimalism. It implements the core components needed for image generation from text prompts: the variational autoencoder (VAE), CLIP text encoder, UNet with attention mechanisms, and the diffusion sampler. The codebase avoids unnecessary abstractions to keep the implementation hackable and easy to follow.
Frequently asked
- What is kjsman/stable-diffusion-pytorch?
- A minimal, readable PyTorch implementation of the Stable Diffusion text-to-image diffusion model.
- Is stable-diffusion-pytorch open source?
- Yes — kjsman/stable-diffusion-pytorch is open source, released under the MIT license.
- What language is stable-diffusion-pytorch written in?
- kjsman/stable-diffusion-pytorch is primarily written in Python.
- How popular is stable-diffusion-pytorch?
- kjsman/stable-diffusion-pytorch has 593 stars on GitHub.
- Where can I find stable-diffusion-pytorch?
- kjsman/stable-diffusion-pytorch is on GitHub at https://github.com/kjsman/stable-diffusion-pytorch.