mikonvergence/DiffusionFastForward

DiffusionFastForward: a free course and experimental framework for diffusion-based generative models

44
/ 100
Emerging

Implements pixel-space and latent-space diffusion variants using PyTorch Lightning, with standalone Colab notebooks covering unconditional generation, conditional image translation, and high-resolution synthesis via VAE compression. Integrates the Hugging Face Diffusers library and enables training on custom datasets without specialized hardware, supporting resolutions from 64×64 to 256×256 with resource budgets under 5GB GPU memory.

678 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

678

Forks

69

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 11, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/mikonvergence/DiffusionFastForward"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.