An Experiment in Generative AI: Craiyon (Formerly Dall-e Mini) — AMT Lab @ CMU (2024)

Dall-e mini, recently renamed Craiyon due to its resemblance to the unrelated Dall-e created by OpenAI, became an internet phenomenon in recent months for its image generation. For those unaware of the technology, users can type a hyper-specific prompt into the image generator, and the AI generates something similar to the image terms.

What It Is

Craiyon, formerly Dall-e mini, is a text-to-image generator created by Boris Dayma originally for a coding competition. He took inspiration from the same technology as OpenAI, wherein this software was created through a machine learning algorithm that was trained on existing images. This means that the algorithm was fed a series of images and was taught how to discern its elements through text. The AI is trained on an immense amount of visual material as well as Natural Language Processing, meaning it can discern and connect language and its visual suggestions. Between the work of Dayma and open source AI communities on Twitter and GitHub, the technology became refined enough to produce recognizable images that gained traction on the internet.


This review is solely for the browser version of this software. The mobile app is currently only available for Android users. Additionally, the use of this software is being tested on the latest version of chrome on MacOs at the time of this article (105.0.5195.102).

A quick internet search typing in “dall-e” yields search results for a webpage, (pictured below) which also notes that the software will be moving to

An Experiment in Generative AI: Craiyon (Formerly Dall-e Mini) — AMT Lab @ CMU (1)

From here, the software offers an intuitive process. The user is cued to type a phrase into the prompt. The user can then either press the orange icon resembling a crayon on the screen or hit enter on the keyboard. It is not instantaneous, thus the user must wait for the image to generate.

The webpage also provides a FAQ (pictured below) that answers a variety of user questions. At the bottom of the webpage, the site provides two email addresses as a point of contact, a newsletter sign-up, a donation button, as well as social media links.

An Experiment in Generative AI: Craiyon (Formerly Dall-e Mini) — AMT Lab @ CMU (2)

Experiment 1: Simplicity

First, I decided to test the AI with a simple command, “cat.” The screen noted that the request would take about two minutes, but the images generated a bit faster than that.

An Experiment in Generative AI: Craiyon (Formerly Dall-e Mini) — AMT Lab @ CMU (3)

The image presents a series of almost-cats, not exactly anatomically correct, particularly regarding facial features. Although the faces are objectively incorrect, details on some of the images are generated fairly well, such as the fur of some and the facial structure of others.

Experiment 2: A Little Extra

Next, I wanted to see how the integrity of the cat would hold if a second element were added. I typed the prompt “cat in a bed.” I decided on this prompt because it requires two simple elements, as well as the interpretation of one object being placed on another. Again, I was given the prompt that the generation should not take long, with a timer on the top right corner of the screen. The results actually took about a minute.

An Experiment in Generative AI: Craiyon (Formerly Dall-e Mini) — AMT Lab @ CMU (4)

The new images were not much different than the previous images, although some cat generation integrity was sacrificed in order to make a vague bed background. However, this indicates that the AI can distinguish the intention of a request, or at least that of a simple one.

An Experiment in Generative AI: Craiyon (Formerly Dall-e Mini) — AMT Lab @ CMU (5)

Experiment 3: Dabbling in Verbs

To observe how the AI holds up with added complexity, I used of the same nouns but added some complexity by including a verb. I wanted to include some form of action and direction to see how the AI captures an extra layer of nuance. Thus, I chose to write “cat jumping into a bed.”

Given the small increase in complexity, Craiyon was unable to retain the realism of a cat’s structure, and even that of the bed in some images. Regardless of realism, the images do provide the grounds for some typical internet humor.

An Experiment in Generative AI: Craiyon (Formerly Dall-e Mini) — AMT Lab @ CMU (6)

Experiment 4: Fine Arts

I would be remiss to not test visual artwork with this software, as AI art is now found in all corners of the art world. Therefore, Craiyon was tested by putting in the title of three different famous artworks of differing styles: Girl with a Pearl Earring, by Johannes Vermeer; Composition with Red, Blue and Yellow, by Piet Mondrian; and Guernica, by Pablo Picasso. This is to not only test its re-creation abilities but whether the prompt attempts to recreate the artwork that is being referenced.

Girl with a Pearl Earring

The Image generator understood exactly what was being asked and delivered a good theoretical replication of the image. However, realistically, it would not pass as a duplicate. It is also important to note that similar images were generated when the prompt was written in full lowercase.

Composition with Red, Blue and Yellow

Craiyon had a difficult time with this prompt. While a still very well-known work of art, the actual title of the piece doubles as a curious request in this context.

An Experiment in Generative AI: Craiyon (Formerly Dall-e Mini) — AMT Lab @ CMU (9)

An Experiment in Generative AI: Craiyon (Formerly Dall-e Mini) — AMT Lab @ CMU (10)

Due to this, I used the same prompt but added “Mondrian” to the end of the phrase to see if the AI could actually distinguish the ambiguity of the phrasing.

An Experiment in Generative AI: Craiyon (Formerly Dall-e Mini) — AMT Lab @ CMU (11)

In doing so, a much more passable recreation of the work was generated.


The AI did a passable job at this painting. While of course it does not provide nearly the level of detail that exists in the image, the general structure of the work is present and easily discernible. Another interesting result of this query is that unlike the previous images, each generated image of Guernica seems to present it as a work in a museum or hanging in a room. This may be a result of the odd dimensions of the work itself.

An Experiment in Generative AI: Craiyon (Formerly Dall-e Mini) — AMT Lab @ CMU (12)

An Experiment in Generative AI: Craiyon (Formerly Dall-e Mini) — AMT Lab @ CMU (13)

Experiment 5: The Final Frontier

While it is interesting to see how machine learning responds to simple commands, complex requests, attempts at re-creation, and how those may be refined in the future, it is equally as interesting to see how the internet is taking advantage of the software. Below is a query that felt appropriate in terms of the internet memes of the world.

An Experiment in Generative AI: Craiyon (Formerly Dall-e Mini) — AMT Lab @ CMU (14)

Final Thoughts

While Craiyon is impressive in its ability to recall and generate images, even the most simple requests do not result in realistic images. Gleaning insight from my experiments, the algorithm has some difficulty discerning requests that are abstract in nature yet specific. Additionally, the more complex the query is, the less accurate the image becomes to real life. While more powerful tools, such as Dall-e, are not yet available to the general public, Craiyon is still an impressive generative AI software, and at the very least, an amusing pastime for casual users.

An Experiment in Generative AI: Craiyon (Formerly Dall-e Mini) — AMT Lab @ CMU (2024)


What is generative AI and example? ›

Generative AI or generative artificial intelligence refers to the use of AI to create new content, like text, images, music, audio, and videos. Generative AI is powered by foundation models (large AI models) that can multi-task and perform out-of-the-box tasks, including summarization, Q&A, classification, and more.

What is GenAI and how does it work? ›

Using algorithmic techniques known as neural networks, GenAI scans data, recognizes patterns, and generates different versions of that data. Where does all this data come from? It comes from vast amounts of human-generated data, and these data are analyzed with algorithms known as Large Language Models, or LLMs.

What is generative AI for dummies? ›

Overall, traditional AI aims to make predictions and deliver results ahead of time. However, Generative AI can perform outside of one specific business function. As its name suggests, 'Generative,'; it usually performs as a generator model that can generate anything using a prompt in real time.

What is the most famous generative AI? ›

Among the best generative AI tools for images, DALL-E 2 is OpenAI's recent version for image and art generation. DALL-E 2 generates better and more photorealistic images when compared to DALL-E. DALL-E 2 appropriately goes by user requests.

Does Siri use generative AI? ›

Apple is revamping Siri with generative AI to catch up with chatbot competitors, report says.

Is ChatGPT a generative AI? ›

ChatGPT is a form of generative AI that helps with content creation and information retrieval. In other words, generative AI is a broad field of artificial intelligence, while ChatGPT is a specific implementation of it. Working with experts can allow you to unlock the potential of generative AI tools.

Is generative AI free to use? ›

Generative AI on Google Cloud

Bring generative AI to real-world experiences quickly, efficiently, and responsibly, powered by Google's most advanced technology and models including Gemini. Plus, new customers can start their AI journey today with $300 in free credits.

What is the difference between generative AI and AI? ›

Traditional AI excels at analyzing data and performing specific tasks, while generative AI focuses on creating new content like text, images, and music.

How does generative AI really work? ›

Generative AI models use machine learning techniques to process and generate data. Machine learning is the foundational component of AI and refers to the application of computer algorithms to data for the purposes of teaching a computer to perform a specific task.

What is the downside of generative AI? ›

One of the foremost challenges related to generative AI is the handling of sensitive data. As generative models rely on data to generate new content, there is a risk of this data including sensitive or proprietary information.

Is Google a generative AI? ›

Soon, when you're looking for ideas, Search will use generative AI to brainstorm with you and create an AI-organized results page that makes it easy to explore. You'll see helpful results categorized under unique, AI-generated headlines, featuring a wide range of perspectives and content types.

Who is the leader in AI right now? ›

Largest AI companies by market cap as of June 2024:

Microsoft. Apple. Alphabet. NVIDIA.

Who are the big players in generative AI? ›

Top Generative AI Companies (91)
  • Grammarly. Artificial Intelligence • Information Technology • Machine Learning • Natural Language Processing • Productivity • Software • Generative AI. ...
  • IMO Health. ...
  • Mixbook. ...
  • Klaviyo. ...
  • MaestroQA. ...
  • Unlearn.AI. ...
  • Mission Cloud. ...
  • Bubble.

What is the best AI tool right now? ›

  • Fliki.
  • Lumen5.
  • Synthesia.
  • DeepBrain AI.
  • Runway.
  • Pictory.
Jun 12, 2024

What is an example of generative AI in the workplace? ›

The Impact of Generative AI: Redefining the Workplace
  • Imagine a marketing team brainstorming ideas for a new product launch. ...
  • Adobe, a leader in creative software, has even integrated Gen AI into its tools, enabling designers to generate unique layouts, color schemes, and even entire design concepts with minimal input.
Apr 29, 2024

What is the difference between AI and generative AI? ›

Traditional AI excels at analyzing data and performing specific tasks, while generative AI focuses on creating new content like text, images, and music.

What is Gen AI in everyday life? ›

Gen. AI is a subject under the Artificial Intelligence that uses Machine Learning (ML) concept to generate human-like content. For example, to create a new image, for writing text, to compose music, and even to generate programming code, Generative AI is changing the way we generate content and use.

What are the 4 types of AI with example? ›

4 main types of artificial intelligence
  • Reactive machines. Reactive machines are AI systems that have no memory and are task specific, meaning that an input always delivers the same output. ...
  • Limited memory machines. The next type of AI in its evolution is limited memory. ...
  • Theory of mind. ...
  • Self-awareness.
Mar 26, 2024


Top Articles
Latest Posts
Article information

Author: Duncan Muller

Last Updated:

Views: 5383

Rating: 4.9 / 5 (79 voted)

Reviews: 94% of readers found this page helpful

Author information

Name: Duncan Muller

Birthday: 1997-01-13

Address: Apt. 505 914 Phillip Crossroad, O'Konborough, NV 62411

Phone: +8555305800947

Job: Construction Agent

Hobby: Shopping, Table tennis, Snowboarding, Rafting, Motor sports, Homebrewing, Taxidermy

Introduction: My name is Duncan Muller, I am a enchanting, good, gentle, modern, tasty, nice, elegant person who loves writing and wants to share my knowledge and understanding with you.