Skip to content

🚀 PyTorch Implementation of "Diffusion Autoencoders: Toward a Meaningful and Decodable Representation"

License

Notifications You must be signed in to change notification settings

Hramchenko/diffusion_editor

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Face Attribute Manipulation with Diffusion Autoencoders and StyleFlow

🚀 Unofficial implementation of Diffusion Autoencoders: Toward a Meaningful and Decodable Representation for face attribute manipulation.

output

Image generation

Download pretrained weights to checkpoints directory.

Run styleflow_script.ipynb.

Training

Download Celeba-HQ dataset.

Run celeba_ae_script.ipynb.

Requirements

  • pytorch
  • torchdiffeq==0.0.1
  • kornia

Acknowledgement

  1. Diffusion Autoencoders: Toward a Meaningful and Decodable Representation.
  2. rosinality/denoising-diffusion-pytorch.
  3. StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows (ACM TOG 2021).

About

🚀 PyTorch Implementation of "Diffusion Autoencoders: Toward a Meaningful and Decodable Representation"

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published