A repo for making a AI-generated draw based on a sound/music file with Wav2CLIP and CLIP.
Repo code based on Clipdraw
The CLIP embedding for audio was from: Wav2CLIP
Differential rendering from clipdraw: diffvg
CLIP from: CLIP
A sample of a drawing created with this sound input birds singing
You can make one with your own sound/music too
@misc{unpublished2021clip,
title = {CLIP: Connecting Text and Images},
author = {Alec Radford, Ilya Sutskever, Jong Wook Kim, Gretchen Krueger, Sandhini Agarwal},
year = {2021}
}
@misc{frans2021clipdraw,
title={CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders},
author={Kevin Frans and L. B. Soros and Olaf Witkowski},
year={2021},
eprint={2106.14843},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
@article{wu2021wav2clip,
title={Wav2CLIP: Learning Robust Audio Representations From CLIP},
author={Wu, Ho-Hsiang and Seetharaman, Prem and Kumar, Kundan and Bello, Juan Pablo},
journal={arXiv preprint arXiv:2110.11499},
year={2021}
}