Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add SPADE normalisation option for diffusion models #372

Closed
virginiafdez opened this issue Apr 11, 2023 · 0 comments · Fixed by #436
Closed

Add SPADE normalisation option for diffusion models #372

virginiafdez opened this issue Apr 11, 2023 · 0 comments · Fixed by #436
Assignees

Comments

@virginiafdez
Copy link
Contributor

Based on the work in: https://arxiv.org/abs/2207.00050
Basically consists on allowing for SPADE normalisation on the upsampling branch of the diffusion model unet.

  • Implement SPADE-norm
  • Allow for SPADE-norm in diffusion models (requires new input arg to the forward method of the Unet, or the coding of a new Unet allowing for this)
  • Allow for SPADE-norm in VAE (in case of latent diffusion models, it might be necessary to condition as well on the VAE side). Same 2 possibilities as in previous point: modify original VAE to allow for input segmentation conditioning, or add new VAE.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
2 participants