← Back
Imagen

Imagen

software

1 creator use or recommend it

1 use 6 mention
Last discussed Aug 24, 2026

Google's AI image generation model that creates high-quality images from text prompts.

Recently discussed in

What creators say

Claire Vo
uses 3
Used for: Podcast thumbnails, image generation with templates Praised: One of the best image generation models

"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 →
PF
Pete Florence
mentioned
Used for: Pre-training vision models to enable transfer learning across tasks vs: Described as a humble precursor to the much larger-scale pre-training seen in...

"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 →
FC
Francois Chaubard
mentioned

"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 →
CF
Chelsea Finn
mentioned
vs: Used as analogy: training from scratch on ImageNet is like early robotics whe...

"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 →
FL
Fei-Fei Li
mentioned
Used for: Training AI algorithms to recognize everyday objects; benchmark for computer vision research Praised: First internet-scale large dataset for AI; convergence with neural network al... vs: Prior to ImageNet, algorithms had very little data to learn from, which was a...

"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 →
Y Combinator
mentioned

"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 →
FC
François Chollet
mentioned

"my mental model for that was ImageNet. I was like, oh, I'm going to make the ImageNet of reasoning"

More from François Chollet →

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
How Followed works →
Get an email when a new creator recommends it

Follow Imagen

Free email updates