The Future of Image Models Is Multimodal
Ideogram CEO Mohammad Norouzi shares his story of growing up in Iran, helping build influential text-to-image models at Google, and ultimately cofounding and running an AI startup. He breaks down the differences between transformer models and diffusion models, as well as the transition from researcher to startup CEO.
June 7, 2024
37 min
11
Full
12 of 100
Episode 11 · June 7, 2024
The Future of Image Models Is Multimodal
0:00 / 37:17
Excerpt playback isn’t available for this episode — use the full-episode link.
Search the Record
Moment search isn’t open for this episode yet
When it opens, you’ll be able to type any phrase and jump straight to the second it was said.
A16z Episodes Around June 7, 2024
Episode 12 of 100 — walk the feed in the order it was published.
37:17This episodeThe Future of Image Models Is Multimodal
Summary
Ideogram CEO Mohammad Norouzi shares his story of growing up in Iran, helping build influential text-to-image models at Google, and ultimately cofounding and running an AI startup. He breaks down the differences between transformer models and diffusion models, as well as the transition from researcher to startup CEO.
Topics
Episode details and artwork are published by the show’s own feed. Sentinel plays short cited excerpts and links every episode back to its publisher.