Here I present image generation using a denoising diffusion probabilistic model which utilizes classifier-free diffusion guidance. The model is trained on the CIFAR-10 dataset at a resolution of 32x32, for a total of around 1 million iterations. For further explanation refer to ffvx43-paper.pdf.
-
Notifications
You must be signed in to change notification settings - Fork 0
Coursework for a 3rd year computer science module at Durham University. Uses a denoising diffusion probabilistic model to generate images from the CIFAR-10 dataset.
License
armypele1/Deep-Learning-Generative-Model
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Coursework for a 3rd year computer science module at Durham University. Uses a denoising diffusion probabilistic model to generate images from the CIFAR-10 dataset.
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published