pytorch-stable-diffusion and stable-diffusion-pytorch

These are competitors—both are independent educational/reference implementations of the same model architecture in PyTorch, serving the same use case of understanding Stable Diffusion from scratch rather than depending on each other or filling different roles.

Maintenance 0/25
Adoption 10/25
Maturity 9/25
Community 25/25
Maintenance 0/25
Adoption 10/25
Maturity 9/25
Community 17/25
Stars: 1,037
Forks: 201
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License: MIT
Stars: 596
Forks: 63
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stale 6m No Package No Dependents
Stale 6m No Package No Dependents

About pytorch-stable-diffusion

hkproj/pytorch-stable-diffusion

Stable Diffusion implemented from scratch in PyTorch

Implements the complete diffusion pipeline including text tokenization (via BPE vocabulary), VAE-based latent encoding/decoding, and cross-attention conditioning between text embeddings and image generation. Supports loading pretrained checkpoints from Hugging Face, including fine-tuned models like InkPunk and Illustration Diffusion variants up to v1.5. Designed as an educational reference implementation that faithfully reproduces the original architecture while remaining compatible with the standard model weights ecosystem.

About stable-diffusion-pytorch

kjsman/stable-diffusion-pytorch

Yet another PyTorch implementation of Stable Diffusion (probably easy to read)

Scores updated daily from GitHub, PyPI, and npm data. How scores work