Images created by a text-to-image AI model called DALL-E mini have been popping up across the internet recently. Despite the similar name, this AI model is not connected to OpenAI or its DALL-E model.

In 2021, OpenAI created the first version of DALL-E, the AI model that is able to understand the relationship between an image and the words used to describe it. The second version called DALL-E 2 was unveiled last April. OpenAI said this version can generate more realistic and accurate images “with four times greater resolution”.

While DALL-E was getting attention, another project was developed to try and reproduce the results of the AI model with a smaller architecture.

Created by machine learning engineer Boris Dayma, Dall-E mini is an open source AI model inspired by OpenAI’s original. The model is trained by looking at millions of images from the internet with their associated captions. Over time, the model learned how to draw an image from the text prompt.

While this is similar to how OpenAI’s models were trained, there are significant differences in both quality and scale. For example, Dayma said the first DALL-E mini model was 27 times smaller than the original DALL-E and was trained on a single TPU v3-8 for only three days.

DALL-E was also trained on 250m pairs of image and text, while DALL-E mini used only 15m pairs.

Unlike OpenAI’s model, DALL-E mini is available to the public, which has led to a wave of comedic and strange images spreading across the internet.

If you haven’t played with dall-E mini I highly recommend it https://t.co/4E5nCvy5ua pic.twitter.com/OzxpUHNOSx

— un jour je serai de retour près de toi (@liebsmakesstuff) June 5, 2022

Dall-E mini isn’t the only AI model to be inspired by OpenAI’s text-to-image model. Last month, Google Research revealed a competitor to OpenAI’s text-to-image system, Imagen. The Google team behind the model said it had an “unprecedented degree of photorealism” and a deep level of language understanding.

Concerns around bias and offensive imagery

Both OpenAI’s Dall-E 2 and Google’s Imagen are not available to the public. OpenAI said it is testing the limitations and capabilities of the model to “develop and deploy AI responsibly”.

This is similar to Imagen, as a preliminary analysis suggested that the model encodes a range of “social and cultural biases” when generating images of activities, events and objects.

Concerns have been raised that this sort of technology could help people spread disinformation online through the use of authentic-looking fake images.

While the images made from DALL-E mini are not nearly as realistic as the more powerful AI models, there is still the risk of bias and offensive imagery being created.

“While the capabilities of image generation models are impressive, they may also reinforce or exacerbate societal biases,” DALL-E mini says on its Hugging Face page. “While the extent and nature of the biases of the DALL·E mini model have yet to be fully documented, given the fact that the model was trained on unfiltered data from the internet, it may generate images that contain stereotypes against minority groups.

“Work to analyse the nature and extent of these limitations is ongoing and will be documented in more detail in the DALL-E mini model card.”

10 things you need to know direct to your inbox every weekday. Sign up for the Daily Brief, Silicon Republic’s digest of essential sci-tech news.

The post Open-source AI-image generator Dall-E mini takes Twitter by storm appeared first on Silicon Republic.