You may have noticed some impressive video memes made with AI in recent weeks. Harry Potter reimagined as a Balenciaga commercial and nightmarish footage of Will Smith eating spaghetti both recently went viral. They highlight how quickly AI's ability to create video is advancing, as well as how problematic some uses of the technology may be. These videos remind me of the moment AI image-making tools became widespread last year, when programs like Craiyon (formerly known as DALL-E Mini) let anyone conjure up recognizable, if crude and often surreal, images, such as surveillance footage of babies robbing a gas station, Darth Vadar courtroom sketches, and Elon Musk eating crayons. Craiyon was an open source knockoff of the then carefully restricted DALL-E 2 image generator from OpenAI, the company behind ChatGPT. The tool was the first to show AI's ability to take a text prompt and turn it into what looked like real photos and human-drawn illustrations.

Evaluating and comparing text-to-image models is a challenging problem. Significant advances in the field have recently been made, piquing interest of various industrial sectors. As a consequence, a gold standard in the field should cover a variety of tasks and application contexts. In this paper a novel evaluation approach is experimented, on the basis of: (i) a curated data set, made by high-quality royalty-free image-text pairs, divided into ten categories; (ii) a quantitative metric, the CLIP-score, (iii) a human evaluation task to distinguish, for a given text, the real and the generated images. The proposed method has been applied to the most recent models, i.e., DALLE2, Latent Diffusion, Stable Diffusion, GLIDE and Craiyon. Early experimental results show that the accuracy of the human judgement is fully coherent with the CLIP-score. The dataset has been made available to the public.

One of the latest applications of Artificial Intelligence (AI) is to generate images from natural language descriptions. These generators are now becoming available and achieve impressive results that have been used for example in the front cover of magazines. As the input to the generators is in the form of a natural language text, a question that arises immediately is how these models behave when the input is written in different languages. In this paper we perform an initial exploration of how the performance of three popular text-to-image generators depends on the language. The results show that there is a significant performance degradation when using languages other than English, especially for languages that are not widely used. This observation leads us to discuss different alternatives on how text-to-image generators can be improved so that performance is consistent across different languages. This is fundamental to ensure that this new technology can be used by non-native English speakers and to preserve linguistic diversity.

I think we can all agree that 2022 is the year of the AI generative art boom. If you've been keeping tabs on social media, you've likely seen some artificial intelligence-inspired memes floating around on your newsfeed. Some of the most widely shared images were developed by DALL-E Mini, now known as Craiyon, a publicly accessible image generation tool that debuted this year. Now, three additional applications, Midjourney, DALL-E 2, and Stable Diffusion have beta versions that are available to play with today! At a distance, it looks like the four tools operate with the same premise -- enter a text-based prompt and receive a series of relevant pictures through advanced machine learning that combs through and learns from millions of images on the internet.

Some artificial intelligences can generate realistic images from nothing but a text prompt. These tools have been used to illustrate magazine covers and win art competitions, but they can also create some very strange results. Nightmarish images of strange creatures keep popping up, sometime known as digital cryptids, named after animals that cryptozoologists but not mainsteam scientists believe may exist somewhere. The phenomenon has garnered national headlines and caused murmuring on social media, so what's going on? One Twitter user asked an AI model called DALL-E mini, since renamed Craiyon, to generate images of the word "crungus".

Whether you like them or not, Artificial Intelligence (AI) image generators have exploded in popularity this year and the technology shows no signs of stopping. So if you're feeling confused about which AI Image generator you should use in 2022, this is a complete guide to the best options out there. A product of the Elon Musk co-founded research lab OpenAI, DALL-E 2, which we'll refer to as simply DALL-E, is the software most people can name when you ask them about AI text-to-image generators. When it launched in April, DALL-E stunned social media with its ability to turn a brief description into a photo-realistic image. For the few people with privileged access to the closed-off tool, DALL-E was so exceptional that it almost felt like magic -- whether that involved generating pictures of "a raccoon astronaut with the cosmos reflecting on the glass of his helmet" or "teddy bears shopping for groceries in Ancient Egypt," all from a simple text prompt.

As if the internet wasn't already bizarre enough, the deluge of weird AI art created by image generators such as DALL·E 2, MidJourney and Craiyon is making things even stranger. From crossbred cartoon characters to surreal food, apocalyptic selfies muppet fashion shows and – erm – people with tennis balls for heads, DALL·E 2 and others seem to be able to create any weird AI art you can describe in their prompt boxes – with varying degrees of success. Of course DALL·E 2 and other AI art generators don't think of these outlandish things themselves and don't'know' what they're helping users to create. They run text prompts through the databases of millions of images and captions that they've learned. This means the results are only as weird as users' own imaginations. There are plenty of existential concerns about where this could all be going and what it means for human artists, but AI won't be taking over the world and turning us into slaves yet.

It only took Matt Laming, a 19-year-old from the United Kingdom, about a month to hit a million followers on Twitter. And all it required was sharing a steady stream of the most outlandish computer-generated images that he and a bunch of internet strangers could think up. In recent weeks, the digital marketing apprentice, better known online as @weirddalle, has shared images depicting things like people vacuuming in the forest, the Demogorgon from Netflix's "Stranger Things" holding a basketball, and a Beanie Baby that looks a lot like Danny DeVito. These and other pictures, which range from ridiculous to disturbing, were created with a freely available artificial intelligence system called Craiyon. To use it, you just type what you'd like it to envision -- "A rainbow lion eating a slice of pizza" -- and it will spit out pictures in response.

You've all seen amazing-looking images like these, entirely generated by an artificial intelligence model. I covered multiple approaches on my channel, like Craiyon, Imagen, and the most well-known, Dall-e 2. Most people want to try them and generate images from random prompts, but the majority of these models aren't open-source, which means we, regular people like us, cannot use them freely. This is what we will dive into in this article. I said most of them were not open-source. Well, Craiyon is, and people have generated amazing memes using it.

I typed "gorilla in a grass skirt having a ball" in a search box on Craiyon.com and the site threw up images of a good looking gorilla, wearing a very Hawaiian grass skirt. But its version of having a ball was not to have a party, but to hold a large colourful ball in its arms. While DALL-E Mini, the original name of Craiyon, is fantastic, it has still got some way to go. It is the open source, free and slightly attenuated version of its mother neural network programme DALL-E 2, created by OpenAI. DALL-E, along with Imagen released by Google Brain to go one up OpenAI, are the latest AI LLMS (large language models), which are stretching the boundaries of what AI can do.