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.
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.
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".
Ideogram is offering two paid plans of either $7 or $15 per month. For more on AI, see our roundup of AI art tutorials.
