Get the latest tech news
Images that Sound: Generating spectrograms that are also images
Images that Sound: Multimodal AI Art
Visual Anagrams, by Geng et al., which uses pretrained diffusion models and compositionality to make multi-view optical illusions. Diffusion Illusions, by Burgert et al., which produces multi-view illusions, along with other visual effects, through score distillation sampling. We adapt their code to make an SDS style baseline for generating images that sound.
Or read this on Hacker News
