Skip to content

Latest commit

 

History

History
21 lines (16 loc) · 735 Bytes

File metadata and controls

21 lines (16 loc) · 735 Bytes

Spectral Guidance for Flexible and Efficient Control of Diffusion Models

Getting started

Check out the standalone example notebooks spectral_guidance_eigenfunctions.ipynband spectral_guidance_gaussian.ipynb.

Train

Training scripts are available in the scripts folder.

Sampling

The main.ipynb notebook provides an example for DDIM sampling with spectral guidance.

Citation

@inproceedings{moreira2026spectralguidance,
  author    = {Moreira, Gabriel and Marques, Manuel and Costeira, Jo{\~a}o Paulo and Xiong, Chenyan},
  title     = {Spectral Guidance for Flexible and Efficient Control of Diffusion Models},
  booktitle = {International Conference on Machine Learning},
  year      = {2026},
}