This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:


trusted source

written by researcher(s)


If AI image generators are so smart, why do they struggle to write and count?

If AI image generators are so smart, why do they struggle to write and count?
AI image produced using the prompt "hyper-realistic ten hands on a picture with text saying hello." Credit: Midjourney, Author provided

Generative AI tools such as Midjourney, Stable Diffusion and DALL-E 2 have astounded us with their ability to produce remarkable images in a matter of seconds.

Despite their achievements, however, there remains a puzzling disparity between what AI image generators can produce and what we can. For instance, these tools often won't deliver satisfactory results for seemingly simple tasks such as counting objects and producing accurate text.

If generative AI has reached such unprecedented heights in creative expression, why does it struggle with tasks even a primary school student could complete?

Exploring the underlying reasons helps sheds light on the complex numerical nature of AI, and the nuance of its capabilities.

AI's limitations with writing

Humans can easily recognize text symbols (such as letters, numbers and characters) written in various different fonts and handwriting. We can also produce text in different contexts, and understand how context can change meaning.

Current AI image generators lack this inherent understanding. They have no true comprehension of what any text symbols mean. These generators are built on trained on massive amounts of image data, from which they "learn" associations and make predictions.

If AI image generators are so smart, why do they struggle to write and count?
AI-generated image produced in response to the prompt 'KFC logo'. Imagine AI

Combinations of shapes in the images are associated with various entities. For example, two inward-facing lines that meet might represent the tip of a pencil, or the roof of a house.

But when it comes to text and quantities, the associations must be incredibly accurate, since even minor imperfections are noticeable. Our brains can overlook slight deviations in a pencil's tip, or a roof—but not as much when it comes to how a word is written, or the number of fingers on a .

As far as text-to-image models are concerned, text symbols are just combinations of lines and shapes. Since text comes in so many —and since letters and numbers are used in seemingly endless arrangements—the model often won't learn how to effectively reproduce text.

The main reason for this is insufficient . AI image generators require much more training data to accurately represent text and quantities than they do for other tasks.

The tragedy of AI hands

Issues also arise when dealing with smaller objects that require intricate details, such as hands.

If AI image generators are so smart, why do they struggle to write and count?
Credit: AI-generated image

In training images, hands are often small, holding objects, or partially obscured by other elements. It becomes challenging for AI to associate the term "hand" with the exact representation of a human hand with five fingers.

Consequently, AI-generated hands often look misshapen, have additional or fewer fingers, or have hands partially covered by objects such as sleeves or purses.

We see a similar issue when it comes to quantities. AI models lack a clear understanding of quantities, such as the of "four".

As such, an image may respond to a prompt for "four apples" by drawing on learning from myriad images featuring many quantities of apples—and return an output with the incorrect amount.

In other words, the huge diversity of associations within the training data impacts the accuracy of quantities in outputs.

If AI image generators are so smart, why do they struggle to write and count?
Credit: AI-generated image

Will AI ever be able to write and count?

It's important to remember text-to-image and text-to-video conversion is a relatively new concept in AI. Current generative platforms are "low-resolution" versions of what we can expect in the future.

With advancements being made in training processes and AI technology, future AI image generators will likely be much more capable of producing accurate visualizations.

It's also worth noting most publicly accessible AI platforms don't offer the highest level of capability. Generating accurate and quantities demands highly optimized and tailored networks, so paid subscriptions to more advanced platforms will likely deliver better results.

Provided by The Conversation

This article is republished from The Conversation under a Creative Commons license. Read the original article.The Conversation

Citation: If AI image generators are so smart, why do they struggle to write and count? (2023, July 5) retrieved 5 December 2023 from
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Explore further

Exploring text-to-audio models to make music from scratch


Feedback to editors