CommunityNews

CommunityNews

Imagen: An AI system that creates photorealistic images from input text

We present Imagen, a text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding. Imagen builds on the power of large transformer language models in understanding text and hinges on the strength of diffusion models in high-fidelity image generation. Our key discovery is that generic large language models (e.g. T5), pretrained on text-only corpora, are surprisingly effective at encoding text for image synthesis: increasing the size of the language model in Imagen boosts both sample fidelity and image-text alignment much more than increasing the size of the image diffusion model. Imagen achieves a new state-of-the-art FID score of 7.27 on the COCO dataset, without ever training on COCO, and human raters find Imagen samples to be on par with the COCO data itself in image-text alignment. To assess text-to-image models in greater depth, we introduce DrawBench, a comprehensive and challenging benchmark for text-to-image models. With DrawBench, we compare Imagen with recent methods including VQ-GAN+CLIP, Latent Diffusion Models, and DALL-E 2, and find that human raters prefer Imagen over other models in side-by-side comparisons, both in terms of sample quality and image-text alignment.

Read in full here:

This thread was posted by one of our members via one of our news source trackers.

Most Liked

AstonJ

AstonJ

It’s amazing how far AI art has come

A photo of a raccoon wearing an astronaut helmet, looking out of the window at night.

Where Next?

Popular Ai topics Top

AstonJ
Well done DeepMind… wonder what else they’re working on… One of biology’s biggest mysteries has been solved using artificial intelligen...
New
First poster: jss
We are in the middle of an AI boom. Machine Learning experts command extraordinary salaries, investors are happy to open their hearts and...
New
New
First poster: bot
DeepMind AI learns simple physics like a baby. Neural network could be a step towards programs for studying how human infants learn.
New
CommunityNews
We present Imagen, a text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understandin...
New
First poster: bot
AI and the Future of Pixel Art. Creative industries are undergoing a 0 to 1 moment. If you didn’t know, now you do. The impact that AI w...
New
CommunityNews
AI supercomputer will use “tens of thousands” of Nvidia A100 and H100 GPUs.
New
First poster: ozornin
They are among 400 artists appealing to Sir Keir Starmer, saying creative industries are threatened.
New
New
First poster: AstonJ
I presented an invited keynote at the AI Engineer World’s Fair in San Francisco this week. This is my third time speaking at the event—he...
New

Other popular topics Top

axelson
I’ve been really enjoying obsidian.md: It is very snappy (even though it is based on Electron). I love that it is all local by defaul...
New
Exadra37
Please tell us what is your preferred monitor setup for programming(not gaming) and why you have chosen it. Does your monitor have eye p...
New
AstonJ
Curious to know which languages and frameworks you’re all thinking about learning next :upside_down_face: Perhaps if there’s enough peop...
New
AstonJ
This looks like a stunning keycap set :orange_heart: A LEGENDARY KEYBOARD LIVES ON When you bought an Apple Macintosh computer in the e...
New
Exadra37
I am asking for any distro that only has the bare-bones to be able to get a shell in the server and then just install the packages as we ...
New
DevotionGeo
The V Programming Language Simple language for building maintainable programs V is already mentioned couple of times in the forum, but I...
New
gagan7995
API 4 Path: /user/following/ Method: GET Description: Returns the list of all names of people whom the user follows Response [ { ...
New
AstonJ
Biggest jackpot ever apparently! :upside_down_face: I don’t (usually) gamble/play the lottery, but working on a program to predict the...
New
CommunityNews
A Brief Review of the Minisforum V3 AMD Tablet. Update: I have created an awesome-minisforum-v3 GitHub repository to list information fo...
New
sir.laksmana_wenk
I’m able to do the “artistic” part of game-development; character designing/modeling, music, environment modeling, etc. However, I don’t...
New