This tech is sick 👀
**Images that Sound: Composing Images and Sounds on a Single Canvas**
Play with sound on 🔊
"tl;dr: We use diffusion models to generate spectrograms that look like images but can also be played as sound."
"Spectrograms are 2D representations of sound that look very different from the images found in our visual world. And natural images, when played as spectrograms, make unnatural sounds. In this paper, we show that it is possible to synthesize spectrograms that simultaneously look like natural images and sound like natural audio. We call these spectrograms images that sound."
"Various musicians have inserted images into spectrograms of their music, including Aphex Twin (go to 5:27), Nine Inch Nails, Venetian Snares, and in Doom's OST. Our work differs from these examples in that our spectrograms both look and sound natural."
https://ificl.github.io/images-that-sound/
#cybersecgirl
ava
npub1f6u…zcka
2024-05-23 07:42:26
Author Public Key
npub1f6ugxyxkknket3kkdgu4k0fu74vmshawermkj8d06sz6jts9t4kslazckaSeen on
wss://relay.noswhere.comPublished at
2024-05-23 07:42:26Event JSON
{
"id": "d504fe0b1a337ddcee924f3c31252be50992c5ceb71adc3eab074d72107fd426",
"pubkey": "4eb88310d6b4ed95c6d66a395b3d3cf559b85faec8f7691dafd405a92e055d6d",
"created_at": 1716442946,
"kind": 1,
"tags": [
[
"t",
"cybersecgirl"
],
[
"r",
"https://v.nostr.build/Z5eEM.mp4"
],
[
"r",
"https://ificl.github.io/images-that-sound/"
]
],
"content": "This tech is sick 👀\n\n**Images that Sound: Composing Images and Sounds on a Single Canvas**\n\nPlay with sound on 🔊\n\nhttps://v.nostr.build/Z5eEM.mp4\n\n\"tl;dr: We use diffusion models to generate spectrograms that look like images but can also be played as sound.\"\n\n\"Spectrograms are 2D representations of sound that look very different from the images found in our visual world. And natural images, when played as spectrograms, make unnatural sounds. In this paper, we show that it is possible to synthesize spectrograms that simultaneously look like natural images and sound like natural audio. We call these spectrograms images that sound.\"\n\n\"Various musicians have inserted images into spectrograms of their music, including Aphex Twin (go to 5:27), Nine Inch Nails, Venetian Snares, and in Doom's OST. Our work differs from these examples in that our spectrograms both look and sound natural.\"\n\nhttps://ificl.github.io/images-that-sound/\n\n#cybersecgirl\n",
"sig": "19c8ec9a1e2636dbd4d39a410f3b57d4ce578821ff7f25a648ae9baa2710d25e929d0ea3e9346a8acd2879384c48f536c69559a586eebed202fe97f30d4b6d7f"
}