Get the latest tech news
Images That Sound
Official repo for Images that sound: a special spectrogram that can be seen as images and played as sound generated by diffusions - IFICL/images-that-sound
We provide the codes (including visualization) and instructions for our approach (multimodal denoising) and two proposed baselines: Imprint and SDS. To create images that sound using our proposed multimodal SDS baseline method, run the code with config file under configs/main_sds/experiment: Note: since our generated images fall outside the distribution, we recommend running more trials (num_samples=16) to select best colorized results.
Or read this on Hacker News
