The advances in AI image generation show no sign of slowing down in 2024. Barely a week after the announcement of Stable Diffusion 3, we have the launch of a newcomer, Ideogram AI, and initial glimpses look pretty impressive.
I have to admit that this is an AI image generator that I have given next to no attention to so far. The list of the best AI image generators seemed to be pretty much sewn up by now, dominated by Midjourney, DALL-E 3 and Adobe's Firefly. As such, it's quite a surprise to see what Ideogram is capable of.
Introducing Ideogram 1.0: the most advanced text-to-image model, now available on https://t.co/Xtv2rRbQXI!This offers state-of-the-art text rendering, unprecedented photorealism, exceptional prompt adherence, and a new feature called Magic Prompt to help with prompting. pic.twitter.com/VOjjulOAJUFebruary 28, 2024
Ideogram AI was founded by former Google engineers and UC Berkeley, Carnegie Mellon University and University of Toronto alumni. It's been developing its tool a while, but it's just announced the launch of the first full version of its image generator alongside a $80 million fundraise.
The company claims that Ideogram provides "unprecedented photorealism, and prompt adherence." To be honest, I'm not 100% sure about that photorealism claim yet. Many of the example images I've seen so far do look impressive, but I couldn't say they look more photorealistic than Midjourney's output. However, it seems that there may be something in that claim about prompt adherence, particularly when it comes to reliability in rendering text. And early results shared online show that Ideogram's ability to interpret longer prompts may match that of Stable Diffusion 3.
It also has a novel tool of its own called Prompt Magic, which in intended to improve prompts to create better images. This recalls DALL-3's ChatGPT-powered natural language capabilities but it can be toggled on and off.
Holy sh*t @ideogram_ai pic.twitter.com/KTZqSi1xPnFebruary 28, 2024
It's incredible how fast AI image generators are improving at making text.I tried out Ideogram 1.0, and I was shocked at how good it turned out!Damn, it's even better than DALL-E and MJ.Prompt:A photo of a stack of 5 book spines, with a variety of book spine designs. Here… pic.twitter.com/AIPPN63T1wMarch 2, 2024
Ideogram just dropped 1.0.The text rendering appears to be much more coherent than DALLE-39 cool examples: pic.twitter.com/346PFQ1hEQMarch 1, 2024
However, some people claim that while Ideogram now appears to be the king of AI image generators when it comes to text generation, Its image output can be more limited in range. Some have called it "cartoonish".
This looks cartoonish? pic.twitter.com/5DjTon37IPMarch 4, 2024
Tried out ideogram ai, it's pretty okay. pic.twitter.com/TGEQpHX8R9March 4, 2024
🚨#PromptShare🚨Coffee.Created by @ideogram_aiPrompt in ALT.#aiart #art #ai #digitalart #generativeart #artificialintelligence #aiartcommunity #aiartists #artist #ArtOfTheDay pic.twitter.com/080TFSFQWWMarch 4, 2024
Ideogram is offering two paid plans of either $7 or $15 per month. For more on AI, see our roundup of AI art tutorials.
Get top Black Friday deals sent straight to your inbox: Sign up now!
We curate the best offers on creative kit and give our expert recommendations to save you time this Black Friday. Upgrade your setup for less with Creative Bloq.
Thank you for reading 5 articles this month* Join now for unlimited access
Enjoy your first month for just £1 / $1 / €1
*Read 5 free articles per month without a subscription
Join now for unlimited access
Try first month for just £1 / $1 / €1
Joe is a regular freelance journalist and editor at Creative Bloq. He writes news, features and buying guides and keeps track of the best equipment and software for creatives, from video editing programs to monitors and accessories. A veteran news writer and photographer, he now works as a project manager at the London and Buenos Aires-based design, production and branding agency Hermana Creatives. There he manages a team of designers, photographers and video editors who specialise in producing visual content and design assets for the hospitality sector. He also dances Argentine tango.