Imagen
Google's AI image generation model that creates high-quality images from text prompts.
Recently discussed in
What creators say
"Imagen 3 is one of the best image gen models. You can now create images with Imagen 3 using a bunch of templates. I use Imagen 3 quite a bit actually for our podcast thumbnails."
More from Claire Vo →"Back in the early 2010s, people would use what was called ImageNet pre-training. It was a large dataset that people would train vision models on, and then people would see a little bit of benefit from starting on training on ImageNet and then usin..."
More from Pete Florence →"Back then the notion was that data is commodity. I already have downloaded ImageNet. How much more data do I possibly need?"
More from Francois Chaubard →"The first major milestone was in 2012 when we saw that a deep learning system trained from scratch first topped the ImageNet benchmark and all of the previous methods for that benchmark were specifically designed for that application."
More from Chelsea Finn →"We led this ImageNet project that collected the first ever internet-scale large dataset for the field of artificial intelligence. ImageNet is a collection of 15 million images, and the goal of ImageNet was to drive machines to recognize everyday o..."
More from Fei-Fei Li →"Is it fair to say that the dataset that was created from embodiment X is similar to the scale of an impact that ImageNet did for vision?"
More from Y Combinator →"my mental model for that was ImageNet. I was like, oh, I'm going to make the ImageNet of reasoning"
More from François Chollet →Keep exploring
Topics
About this data
- ✓44,000+ mentions extracted from real podcast transcripts
- ✓Every quote links to the source episode
- ✓Sponsored mentions are always labeled
- ✓Critical takes are shown, never filtered out