This repository implements a Diffusion Probabilistic Model (DDPM) for image generation, featuring UNet architecture and cosine noise scheduling. It supports training on the Flowers102 dataset and generates 64x64 images. TensorBoard logging and checkpoints are included.
-
Notifications
You must be signed in to change notification settings - Fork 0
This repository implements a Diffusion Probabilistic Model (DDPM) for image generation, featuring UNet architecture and cosine noise scheduling. It supports training on the Flowers102 dataset and generates 64x64 images. TensorBoard logging and checkpoints are included.
License
kwdahun/DDPMImplementation
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
This repository implements a Diffusion Probabilistic Model (DDPM) for image generation, featuring UNet architecture and cosine noise scheduling. It supports training on the Flowers102 dataset and generates 64x64 images. TensorBoard logging and checkpoints are included.
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published