2min chapter

The Gradient: Perspectives on AI cover image

Max Woolf: Data Science at BuzzFeed and AI Content Generation

The Gradient: Perspectives on AI

CHAPTER

How to Scale a Large Texturing Model to Maintain Performance

The secret towards more efficient generation will be just high pre-training, especially on image generations. There's a very strong motive to pursue making them smaller and maintaining the kind of performance we're seeing out of these super large models. And there's a lot of tricks. Like the big trick with I saw with like image in which is what Google's new texturing model they announced a few days ago.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode