Introducing: The AI Generation
All about AI and the algos that love them
AI is everywhere right now. So why not jump on that bandwagon early? With my no-fluff, conversational writing style, I will try and give some understanding to this new tech. It feels to me like Crypto did in the mid-20-teens.
What is it?
Generative AI refers to a category of artificial intelligence (AI) algorithms that generate a desired output based on the data they have been trained on. The inputs are called Prompts. The new content generated by these prompts is called Generative Artificial Intelligence. This newly created content can be in the form of images, text, audio, and more.
Some Uses for Generative AI art
Automatically creating digital artwork, illustrations, and designs. Use wherever you’d like.
Generating original visual content for film and video games.
Creating unique patterns, textures, and backgrounds for design projects.
Automatically generating digital paintings, sketches, and other forms of fine art.
Creating custom digital animations and special effects.
Automating the process of designing logos and branding materials.
Generating randomized visual content for websites, social media platforms, and other online media.
Automatically creating digital wallpaper and other decorative elements for personal and commercial use.
Creating AI-generated music videos and other multimedia projects.
Automatically generating original visual content for advertisements and marketing campaigns.
10 Uses for ChatGPT
Answering questions and providing information: ChatGPT can be used as a virtual assistant or knowledge base for answering a wide range of questions.
Generating natural language text: ChatGPT can be used for text generation tasks such as writing stories, composing poetry, summarizing articles, and much more.
Chatbots and customer service: ChatGPT can be integrated into chatbots and other customer service systems to provide fast and accurate answers to customer queries.
Language translation: ChatGPT can be trained in multiple languages, making it a powerful tool for real-time machine translation.
Content moderation: ChatGPT can be used to automatically detect and remove harmful or inappropriate content in chat rooms, forums, and other online communities.
Sentiment analysis: ChatGPT can be used to analyze and categorize opinions, sentiments, and emotions expressed in text data, such as customer feedback or social media posts.
Personalization and recommendation systems: ChatGPT can be used to generate personalized content and product recommendations based on user preferences and behavior.
Summarization and abstract generation: ChatGPT can be used to automatically generate short summaries of long texts, such as news articles or scientific papers.
Speech recognition and transcription: ChatGPT can be integrated into speech recognition systems to transcribe and analyze spoken language.
Automated writing and content creation: ChatGPT can be used to automate the process of writing articles, blog posts, product descriptions, and other forms of written content.
10 Uses for AI using Audio
Speech recognition: AI can be used to transcribe spoken language into written text, enabling tasks such as automatic captioning, dictation, and call center automation.
Speech synthesis: AI can be used to generate speech from text, enabling the creation of virtual assistants, speech-enabled devices, and more.
Music generation: AI can be used to compose original music and generate variations on existing compositions.
Audio classification and analysis: AI can be used to classify audio data, such as speech and music, and analyze its content, such as sentiment and topics.
Voice biometrics: AI can be used to identify individuals based on their unique voice patterns, enabling secure authentication for voice-enabled devices and applications.
Noise reduction: AI can be used to remove unwanted background noise from audio signals, improving the quality of voice and music recordings.
Audio search and retrieval: AI can be used to enable fast and accurate search and retrieval of audio content, such as music and podcasts, based on spoken or written queries.
Speech-to-text translation: AI can be used to translate speech in one language into text in another language, enabling real-time communication across language barriers.
Voice-enabled interfaces: AI can be used to create voice-enabled interfaces, such as voice assistants, enabling hands-free interaction with technology.
Audio-based emotion recognition: AI can be used to detect emotions such as happiness, sadness, anger, and more, based on the audio features of speech.
I’ll be writing about a lot of these uses in upcoming newsletters.
How to use Midjourney?
This is an example of a prompt I wrote to get a nice fall forest picture using the program called Midjourney:
a photograph of a stunning fall scene in the eastern USA, a forest of red with burning maple leaves, larch trees, heavy undergrowth, magical hour, shot with a high-end camera --ar 3:2 --chaos 66
This was the output:
In the coming newsletters, which will come out on Saturdays, I’ll be showing you how to use this new technology to write your prompts to get the best images possible. And some examples of what to try out. To use Midjourney, you need to have the Discord app/software on your computer. It is free and safe.
Once you have your discord account, you can go to the Midjourney website and “Join the Beta“.
You will be able to use Midjourney by clicking on any of the Newcomer Rooms and you are ready to create.
You’ll go into a room of scrolling pictures with a lot of other people. As a newcomer, you are given around 25 pictures to generate, and try out the service, for free!
Enter /imagine in the prompt bar at the bottom of the page.
Then you enter your prompt. See what prompts other members are using and when you see something you’d like to make for yourself, try a version of their prompt. Here are a few to start with that give pretty remarkable pictures:
dinosaur T-Rex chases a Jeep car down a road in the jungle, front view, action, speed bright colors, rain
a painting of a giraffe with flowers on its head, a hyperrealistic painting, inspired by Mike Winkelmann, Shutterstock contest winner, maximalism, high-quality 3d render, a beautiful artwork illustration, colorful painting, abstract 3 d artwork, painted on a giant wall, funny illustration
Charleston South Carolina rainbow row houses
professional photo of Albert Einstein looks like a modern geek guy with a T-shirt, jeans, and headphones on their neck, staying on Shibuya street in Tokyo Night, photorealistic, 32k, high details, professional studio lighting, cinematic, 50 mm lenses, --ar 3:2 --q 2 --v 4
an urban street in causeway bay of Hong Kong, painting, out of focus, bright, colorful
blue yellow and grey gears, high definition product image, shiny surfaces, raytracing, 4k, no background
1950s family barbeque in a residential neighborhood, a huge nuclear explosion in the background, Dad grilling burgers and laughing, in the style of Wes Anderson, atomic bomb explosion towering mushroom cloud, full shot, hyperrealism, hyper-realistic, cinematic style, hyper-realistic, highly detailed 4k color cinematic production still --ar 3:2 --q 2 --s 250
plums, cherries, apricots photorealistic --ar 3:2 --s 750
Playful lion cub, ambient light, Nikon 15mm f/1.8G" Professional photography, bokeh, natural lighting, canon lens, shot on DSLR 64 megapixels sharp focus
vast jungle landscape, palm trees with blue leaves, gray skies, blue haze, electric fences with orange glow --v 4 --ar 3:2
a chicken face, looking like it is in love, ultra-realistic, 4k, with many details
You can choose a favorite Comic artist and emulate their style by using "character by…" "cartoon character by…" and "comic book superhero by…" and then the artist name. An example prompt would be:
/imagine prompt comic book illustration, james hetfield, horror, in the style of William Gainese, full color, horror style
These are the images created by the above prompt:
Here is a list of more Comic Book and Cartoon artists to try:
Neal Adams, Charles Addams, Brian Allen, Artgerm, AssasinMonkey, Peter Bagge, Ralph Bakshi, Carl Barks, Jon Bauer, Jasmine Becket-Griffith, Ludwig Bemelmans, Elsa Beskow, Enki Bilal, Quentin Blake, Barry Blitt, Don Bluth, Mary Blair, John Blanche, Brian Bolland, Mark Brooks, Tim Burton, John Buscema, Randolph Caldecott, J. Scott Campbell, Pascal Campion, Milton Caniff, Eric Carle, cgsociety, Roz Chast, Howard Chaykin, Frank Cho, Craola, Robert Crumb, Farel Dalrymple, Geof Darrow, Alan Davis, Steve Dillon, Tony DiTerlizzi, Steve Ditko, Kevin Eastman, Will Eisner, Hal Foster, Dave Gibbons, Matt Groening, William Gropper, George Grosz, Butch Hartman, Hergé, Jamie Hewlett, Stephen Hillenburg, Adam Hughes, Alexander Jansson, Mike Judge, Jean Jullien, M.W. Kaluta, Brian Kesinger, Jon Klassen, Bryan Konietzko, Andy Kubert, Abigail Larson, Gary Larson, Jeff Lemire, Roy Lichtenstein, Michal Lisowski, Cory Loftis, Kevin Maguire, Bill Mantlo, Craig McCracken, Todd McFarlane, Aaron McGruder, Mike Mignola, Frank Miller, Jean-Baptiste Monge, Dustin Nguyen, Paul Pope, Beatrix Potter, John Romita Jr., Tony Sart, Marjane Satrapi, Richard Scarry, Charles M. Schulz, Dr. Seuss, Walt Simonson, Art Spiegelman, Jim Starlin, William Steig, Ralph Steadman, Saul Steinberg, Jim Steranko, Rebecca Sugar, Jillian Tamaki, Shaun Tan, Jacques Tardi, Genndy Tartakovsky, Piper Thibodeau, Frank Thorne, Bruce Timm, Sergio Toppi, Garry Trudeau, Albert Uderzo, Tomi Ungerer, Jhonen Vasquez, Charles Vess, Pendleton Ward, Bill Watterson, Chris Ware, Al Williamson, Bill Willingham, Basil Wolverton, Ashley Wood, Wally Wood, Bernie Wrightson
You click on the pic you generate from your prompt, and open it in your browser (button below pic). If you want to save it to your computer, just right-click and save.
Instead of using a free public domain picture website, I use Midjourney to illustrate my newsletters now. Check out the other articles in this niche at https://pau1.substack.com/s/the-ai-generation
Consider subscribing. Comment and suggest material you’d like to learn more about. Peace!