Perhaps not surprisingly, multimodal systems like mmc4 and OpenFlamingo have several possible applications that are different from other, more fundamental text-only language frameworks and models.

Source: https://www.geekwire.com/2023/ai2-researchers-release-new-multimodal-approach-to-boost-ai-capabilities-using-images-and-audio/

Videos are 53 times more likely to secure a first-page and generate 41% more clicks than text-only pages.

Source: https://www.chiangraitimes.com/how-to/how-to-optimize-your-webcam-for-content-creator-tips-for-youtubers/

You’ll see images from all over the fediverse and even from Mastodon, but text-only posts are filtered.

Source: https://www.infoworld.com/article/3687129/should-you-leave-facebook-twitter-instagram-for-the-fediverse.html