Let's Experiment with DALL-E 3 and Llama 3!

Jonathan Mast from White Beard Strategies updated me this morning about recent developments with Meta AI, which prompted me to rerun an experiment I originally conducted in January 2024. 🤖
At that time, I had used the same prompt across three platforms: OpenAI and Bing, which utilize DALL-E 3 technology, and Meta AI, powered by Llama 3 technology. 🐝 🐝 🐝

In January, OpenAI precisely delivered what I requested—three bees in a jar—without additional elements. Bing's results included three bees, not inside but outside the jar, along with items related to bee activity, like honey 🍯 and oranges🍊, which I had mentioned as desirable background elements. Meta AI's response, however, featured more than three bees either on or in the jar, and this time, they were proportionately depicted, which was an improvement.
The background settings were also notable. Previously, Meta AI chose a simple backdrop, but today, it selected a complex office environment reminiscent of one Einstein might prefer, complete with a light bulb—likely because bees are positively phototactic and are attracted to light. 💡

A consistent detail in all results this time was the absence of any brand names on the jars, such as “Ball,” which had appeared previously.

Reflecting on these responses, it's fascinating to consider the implications of these AI tools as they evolve. Why do you think each AI interpreted the prompt so differently? What does this tell us about the way artificial intelligence understands context and creativity? Join the discussion below and share your thoughts or any experiments you’ve conducted. Who knows—your insights might just shape the next experiment! 🤓


hashtag#generativeai hashtag#dalle3 hashtag#creative hashtag#digitalmarketing hashtag#openai hashtag#bing hashtag#metaai

Original from January 2024

Updated image, same prompt — April 2024

"Generating Creative Images with DALL-E 3," has achieved the #4 spot on Amazon's Hot New Release list!

I'm thrilled to share that my latest publication, "Generating Creative Images with DALL-E 3," has achieved the #4 spot on Amazon's Hot New Release list! 🎉

This accomplishment is not just a personal milestone but a testament to the growing importance and enthusiasm for generative AI technologies in creative fields.
In writing this book, my goal was to demystify the capabilities of DALL-E 3 for artists, designers, educators, and business professionals alike, showcasing how it can be leveraged to unlock unparalleled creativity and innovation. As we stand on the brink of a new era where technology and art converge in ways previously unimaginable, I am excited to contribute to the conversation and development in this space.

I invite my network to join me in exploring the possibilities that DALL-E 3 and generative AI offer. Together, we can push the boundaries of creativity and innovation.

#GenerativeAI #DALLE3 #Innovation #FullSailAlum #CreativeTechnology #ArtificialIntelligence #BookLaunch #AmazonHotNewRelease

A Comparative Study of DALL-E 3 on OpenAI vs Bing

🍒 Exploring the Depths of AI-Generated Art: A Comparative Study of DALL-E 3 on OpenAI vs Bing

🌟 Test Results!
I recently embarked on an intriguing journey, putting two AI
powerhouses to the test: DALL-E 3 on OpenAI versus DALL-E 3 on Bing. My goal?
To see which platform more accurately captures and interprets creative prompts.

🎨 The Prompt: A close-up of
a red cherry falling into a glass of water, with a black background, set
against a black background, low-key lighting, fast shutter speed.

🔍 What Went Down: Here's where it
gets interesting. OpenAI's DALL-E 3? Nailed it!

🔀 Bing's take? It went all out with lots of cherries in the mix, 3 out of 4 times. Looks cool but not what I was after.

💡 Thought Bubble: As we keep playing
with AI-made art, it's clear how much the details matter. Each one's got its
own flair, making the AI art scene a wild mix of surprises.

👀 Keep your eyes peeled for more of my AI escapades, and hit me up with your thoughts or your own AI experiments!

DID YOU KNOW? DALL-E 3 will generate other sizes? 💡

DALL·E-3 accepts three different image sizes: 1024px by 1024px (default), 1792px by 1024px, and 1024px by 1792px.

The trick is, you have to tell DALL-E 3 that you want to generate that specific size, otherwise it will (usually) default to 1024x1024.

Ok, so generative AI is still not the best at spelling, but with some patience and iteration, we'll get there! 😄

#dalle3 #aicommunity #techadvancements #digitalmarketing

See examples at this LinkedIn post.