Total Tech Solutions

wespeak

What got you into AI?

by

How I Got Into AI

Around November 2022, I first heard about AI—specifically, ChatGPT. Computers have always been my thing: for entertainment, learning, business, and fun. I enjoy seeing what I can pull off with the tools I’m given, and this was no different. Although my memory is a bit foggy—partly because I’m blind from birth and had a stroke in January 2021 that affected my balance due to life (and, well, shit happens sometimes—ha-ha, sorry)—I recall being intrigued by the possibilities AI offered.

Today, I have a lot going on but much less stress in my life, aside from the usual problems we all face. I might need surgery in the spring, moving is challenging, and I have a big trip in a week. But discovering ChatGPT was a game-changer. It was like interacting with a computer that basically acts like a person. Back then, I had to really go through a lot of trouble to make an image; it is so easy now. It really helps me a lot to try and think of technology from an average user’s standpoint—nothing too deep there. I used to experiment with back-translating things and asking ChatGPT all sorts of questions:

  • "What are 10 methods that writers use in their work?"
  • "How far is the largest star?"
  • "What happens when two black holes collide?"

One of the most fascinating facts I learned is that if the largest star in the universe were in place of our sun, it would extend past Jupiter. That’s mind-blowing and a good reminder of how small we are in a universe that’s been around for billions of years. Makes paying rent not seem so bad!

From 2022 to 2024, I delved into voices, programming, languages, and text—getting pretty good at all of it. I had played with some early AI image models but wasn’t on the Be My Eyes beta, so I had to wait until August 2023. When I realized it was possible to create images using Bing, I could have Be My AI describe them. If the description was off, I’d keep working on it. This was probably between August and October 2023. I even had an interview for my podcast with Mike Buckley of Be My Eyes. It was still pretty new to me, and I think I knew half as much about it at that point.

Creating images is the most fun for me, along with exploring languages, deep questions, and prompting. I see such potential in this technology that image creation is just a small part of the big picture. Even with all its flaws, I find image creation therapeutic. I can do it anywhere—in any airport or even high in the sky. It really puts my anxiety at bay, and people love it. Even if the images aren’t that good, they still bring smiles to those who see them.

Some people get overly upset about it all. I have a website called art by keen dot com where I sell prints of my art, but it hardly sells anything. I’ll probably take it down soon; it’s not worth the $79 a month I pay for it. Either way, it’s something people are interested in learning, and it’s so simple and accessible to do.

I envision an app that paints or draws for you. You launch it, talk to it about making images, it creates the image, and then tells you about it. Maybe you can share it with someone. Including that as an internal feature of a current app would be cool. If that works out, how about a 20% cut? Just kidding, but that’s how my brain works.

I strive to be open and honest about this technology. I may get some things wrong, but we all do. I admit when I’m wrong—or at least I try to. One of the early things I did with images on Facebook was to describe local photographers’ photos using AI. I’d find a cool photo and leave the description—maybe with a message—all created by AI on the post. Those photographers are popular. One of them is a man in Fort Worth, Texas, named Bryan Luenser.
Bryan is a retired accountant who now enjoys his hobby of photography. I think he’s so busy with this joy that he may have to retire from it someday. We finally met—I had him on an interview on this podcast, which at the time was called WeSpeak Live. This was in November 2023. We met for breakfast in December—I remember the date—and I had some good news around then, so it’s fixed in my memory.

Bryan is another super person. Nowadays, it’s a good idea to surround yourself with good people. It takes a lot of energy to bring on new friends, so just stick with the winners. That’s one thing I’m proud of in my life: I’ve always been able to get along with most people, even if we are vastly different. But I have some good folks in life today!

Around the same time, I had just taken a prompting course on a website called Coursera. It was a fully accessible course, and the lectures were the best part. I still need to go back and finish all of those courses, but I got a little distracted. I emailed the professor who teaches the course, Dr. Jules White of Vanderbilt University. He teaches the classes on Coursera and is a professor of computer science at Vanderbilt University in Nashville, Tennessee. I’ll put some links to everything in the comments once I have it all together.

Jules is one of my fans nowadays and very supportive.

I think this is an interesting story. I try to keep it engaging, but I am who I am. I have a lot of good instincts, but I’m just an everyday person. I don’t have a college degree; I just have 50 years of life experience, blindness, pain, and love. That’s what keeps me going, including my wife Mindy and kids.

I spoke to Dr. White in December on a Zoom call for like an hour or two. He was totally fascinated with me. He’s very smart about everything, but blindness is a niche—like wheelchairs for me; I don’t know anything, so sometimes I can only go on the knowledge I have, which is sometimes none. That is true on a lot of topics—for me, I don’t know it all.
Oops, that is all of the Eleven labs voice for this month on Eleven labs, the next acount level upgrade is $99 a month and that isn’t in the budget!

Support AI For The Blind. by contributing to their tip jar: https://tips.pinecast.com/jar/wespeak

This podcast is powered by Pinecast.

Describe it!

by

Another great Saturday almost wrapped up. I came across a post earlier today about how hard it can be to get accurate image descriptions of people. It’s becoming tougher as more rules get put in place for the censored models. But there are some free uncensored alternatives out there—I’ll drop a link for those below. Keep an eye on the comments for any updates or extra info I might add.

I try to keep things as user-friendly as possible, so you can also check out the podcast link for a basic transcript in my AI voice, plus a bonus trick for your wearables.

I’ve worked on a solution and wanted to share it with you. It’s a good idea to save prompts, whether in your phone’s notes app or on your computer—I’ve got a bunch saved for some pretty wild tasks. Saving prompts like this one can come in handy. If you paste this prompt into the question field when generating an image of a person, you’ll get a more detailed response.

Our blind youth must be having a blast with this technology! There’s so much visual info out there that we miss out on, but they’re diving right in.

Well, give this Prompt a try, i paste it in Be My AI with an image, sure wish there were presets:

i know a lot of people like to use there voice with there computer so I wantedd to include this here, some tips on how you could shorten this prompt to a few voice commands that you can remember easley or less challenging way, use english and include slang if it works, the prompt you create is for a audience of all ages with various experience levels simple casual is usually best, rewrite this prompt to create better content, this will bbe used for a podcast, ai for the blind with over 6000 listens in a little over a year:

:

Comprehensive Image Description Prompt

*"In the image, there is a [man/woman/non-binary individual/group of people] [standing/sitting/engaged in an activity] within a [describe the setting: indoor, outdoor, specific location] environment. The individual(s) appear to be [age range: child, teenager, young adult, middle-aged, senior], and they have [hair length: short, medium, long] [hair style: straight, wavy, curly, styled, unstyled] hair that is [hair color and texture: blonde, brunette, red, black, graying, thick, thin].

They are dressed in [describe clothing in detail: color, style, type of garments, patterns, accessories]. For example, they might be wearing a [color] [type of clothing, e.g., casual t-shirt, formal suit, athletic wear] with [additional details like patterns, textures, layers]. Accessories such as [glasses, hats, jewelry, scarves, belts] are present, enhancing their [casual/formal/professional/relaxed] appearance.

The person’s facial expression conveys [emotion: smiling, serious, thoughtful, joyful, contemplative], and their [specific facial features: eye color, presence of glasses, facial hair, makeup] are notable. Their posture is [upright, relaxed, slouched], indicating they are [engaged in conversation, relaxed, focused, active].

Their body language suggests they might be [performing an activity: talking, working, reading, walking, exercising], and they are interacting with [objects they are holding or using: a smartphone, book, cane, laptop, sports equipment]. These interactions imply they are [specific activity: browsing the internet, reading a book, navigating their environment, working on a computer, playing a sport].

Physical characteristics of the individual(s) include [skin tone, height, body type: slender, athletic, average build, muscular, petite]. These features contribute to their overall appearance in the image.

The background of the image features [detailed description of surroundings: architectural elements like buildings or furniture, natural elements like trees or water, interior details like room layout or decorations]. This provides context for the scene, indicating whether it is set indoors or outdoors, in an urban or natural environment.

Lighting in the image is [type of lighting: bright, dim, natural, artificial], which creates [effects: shadows, highlights, soft illumination] on their features and the surroundings, adding depth and mood to the scene.

Overall, the atmosphere of the image feels [describe the mood: calm, energetic, lively, serene, bustling], and the individual(s) appear [describe their demeanor: focused, engaged, happy, contemplative, active]. Additional observations include [any unique details or context that enhance understanding, such as weather conditions, time of day, cultural elements].*

Usage Example:

*"In the image, there is a woman standing in a sunlit park. She appears to be in her early thirties, with long, wavy brunette hair that cascades over her shoulders. She is wearing a light blue summer dress with floral patterns and a pair of white sandals, giving her a relaxed and cheerful appearance. Her facial expression is joyful, with a bright smile and sparkling brown eyes framed by subtle makeup. She stands upright with a relaxed posture, holding a red umbrella in one hand and a wicker basket in the other, suggesting she might be preparing for a picnic.

Her skin tone is fair, and she has a slender build. The background features lush green trees, blooming flowers, and a paved walking path, indicating a peaceful outdoor setting. The natural sunlight casts soft shadows, enhancing the vibrant colors of the scene. Overall, the mood of the image is serene and happy, with the woman appearing content and enjoying a beautiful day in the park."*
Comprehensive Image Description Prompt

"In the image, there is a [man/woman/non-binary individual/group of people] [standing/sitting/engaged in an activity] within a [describe the setting: indoor, outdoor, specific location] environment. The individual(s) appear to be [age range: child, teenager, young adult, middle-aged, senior], and they have [hair length: short, medium, long] [hair style: straight, wavy, curly, styled, unstyled] hair that is [hair color and texture: blonde, brunette, red, black, graying, thick, thin].

They are dressed in [describe clothing in detail: color, style, type of garments, patterns, accessories]. For example, they might be wearing a [color] [type of clothing, e.g., casual t-shirt, formal suit, athletic wear] with [additional details like patterns, textures, layers]. Accessories such as [glasses, hats, jewelry, scarves, belts] are present, enhancing their [casual/formal/professional/relaxed] appearance.

The person’s facial expression conveys [emotion: smiling, serious, thoughtful, joyful, contemplative], and their [specific facial features: eye color, presence of glasses, facial hair, makeup] are notable. Their posture is [upright, relaxed, slouched], indicating they are [engaged in conversation, relaxed, focused, active].

Their body language suggests they might be [performing an activity: talking, working, reading, walking, exercising], and they are interacting with [objects they are holding or using: a smartphone, book, cane, laptop, sports equipment]. These interactions imply they are [specific activity: browsing the internet, reading a book, navigating their environment, working on a computer, playing a sport].

Physical characteristics of the individual(s) include [skin tone, skin color, a guess at there race even if that isn’t allways right, height, body type: slender, athletic, average build, muscular, petite]. These features contribute to their overall appearance in the image.

The background of the image features [detailed description of surroundings: architectural elements like buildings or furniture, natural elements like trees or water, interior details like room layout or decorations]. This provides context for the scene, indicating whether it is set indoors or outdoors, in an urban or natural environment.

Lighting in the image is [type of lighting: bright, dim, natural, artificial], which creates [effects: shadows, highlights, soft illumination] on their features and the surroundings, adding depth and mood to the scene.

Overall, the atmosphere of the image feels [describe the mood: calm, energetic, lively, serene, bustling], and the individual(s) appear [describe their demeanor: focused, engaged, happy, contemplative, active]. Additional observations include [any unique details or context that enhance understanding, such as weather conditions, time of day, cultural elements].*

Usage Example:

*"In the image, there is a woman standing in a sunlit park. She appears to be in her early thirties, with long, wavy brunette hair that cascades over her shoulders. She is wearing a light blue summer dress with floral patterns and a pair of white sandals, giving her a relaxed and cheerful appearance. Her facial expression is joyful, with a bright smile and sparkling brown eyes framed by subtle makeup. She stands upright with a relaxed posture, holding a red umbrella in one hand and a wicker basket in the other, suggesting she might be preparing for a picnic.

Her skin tone is fair, and she has a slender build. The background features lush green trees, blooming flowers, and a paved walking path, indicating a peaceful outdoor setting. The natural sunlight casts soft shadows, enhancing the vibrant colors of the scene. Overall, the mood of the image is serene and happy, with the woman appearing content and enjoying a beautiful day in the park."

i know a lot of people like to use there voice with there computer so I wantedd to include this here, some tips on how you could shorten this prompt to a few voice commands that you can remember easley or less challenging way, use english and include slang if it works, the prompt you create is for a audience of all ages with various experience levels simple casual is usually best, rewrite this prompt to create better content, this will bbe used for a podcast, ai for the blind with over 6000 listens in a little over a year:

:

Comprehensive Image Description Prompt

*"In the image, there is a [man/woman/non-binary individual/group of people] [standing/sitting/engaged in an activity] within a [describe the setting: indoor, outdoor, specific location] environment. The individual(s) appear to be [age range: child, teenager, young adult, middle-aged, senior], and they have [hair length: short, medium, long] [hair style: straight, wavy, curly, styled, unstyled] hair that is [hair color and texture: blonde, brunette, red, black, graying, thick, thin].

They are dressed in [describe clothing in detail: color, style, type of garments, patterns, accessories]. For example, they might be wearing a [color] [type of clothing, e.g., casual t-shirt, formal suit, athletic wear] with [additional details like patterns, textures, layers]. Accessories such as [glasses, hats, jewelry, scarves, belts] are present, enhancing their [casual/formal/professional/relaxed] appearance.

The person’s facial expression conveys [emotion: smiling, serious, thoughtful, joyful, contemplative], and their [specific facial features: eye color, presence of glasses, facial hair, makeup] are notable. Their posture is [upright, relaxed, slouched], indicating they are [engaged in conversation, relaxed, focused, active].

Their body language suggests they might be [performing an activity: talking, working, reading, walking, exercising], and they are interacting with [objects they are holding or using: a smartphone, book, cane, laptop, sports equipment]. These interactions imply they are [specific activity: browsing the internet, reading a book, navigating their environment, working on a computer, playing a sport].

Physical characteristics of the individual(s) include [skin tone, height, body type: slender, athletic, average build, muscular, petite]. These features contribute to their overall appearance in the image.

The background of the image features [detailed description of surroundings: architectural elements like buildings or furniture, natural elements like trees or water, interior details like room layout or decorations]. This provides context for the scene, indicating whether it is set indoors or outdoors, in an urban or natural environment.

Lighting in the image is [type of lighting: bright, dim, natural, artificial], which creates [effects: shadows, highlights, soft illumination] on their features and the surroundings, adding depth and mood to the scene.

Overall, the atmosphere of the image feels [describe the mood: calm, energetic, lively, serene, bustling], and the individual(s) appear [describe their demeanor: focused, engaged, happy, contemplative, active]. Additional observations include [any unique details or context that enhance understanding, such as weather conditions, time of day, cultural elements].*

Usage Example:

*"In the image, there is a woman standing in a sunlit park. She appears to be in her early thirties, with long, wavy brunette hair that cascades over her shoulders. She is wearing a light blue summer dress with floral patterns and a pair of white sandals, giving her a relaxed and cheerful appearance. Her facial expression is joyful, with a bright smile and sparkling brown eyes framed by subtle makeup. She stands upright with a relaxed posture, holding a red umbrella in one hand and a wicker basket in the other, suggesting she might be preparing for a picnic.

Her skin tone is fair, and she has a slender build. The background features lush green trees, blooming flowers, and a paved walking path, indicating a peaceful outdoor setting. The natural sunlight casts soft shadows, enhancing the vibrant colors of the scene. Overall, the mood of the image is serene and happy, with the woman appearing content and enjoying a beautiful day in the park."*
Comprehensive Image Description Prompt

"In the image, there is a [man/woman/non-binary individual/group of people] [standing/sitting/engaged in an activity] within a [describe the setting: indoor, outdoor, specific location] environment. The individual(s) appear to be [age range: child, teenager, young adult, middle-aged, senior], and they have [hair length: short, medium, long] [hair style: straight, wavy, curly, styled, unstyled] hair that is [hair color and texture: blonde, brunette, red, black, graying, thick, thin].

They are dressed in [describe clothing in detail: color, style, type of garments, patterns, accessories]. For example, they might be wearing a [color] [type of clothing, e.g., casual t-shirt, formal suit, athletic wear] with [additional details like patterns, textures, layers]. Accessories such as [glasses, hats, jewelry, scarves, belts] are present, enhancing their [casual/formal/professional/relaxed] appearance.

The person’s facial expression conveys [emotion: smiling, serious, thoughtful, joyful, contemplative], and their [specific facial features: eye color, presence of glasses, facial hair, makeup] are notable. Their posture is [upright, relaxed, slouched], indicating they are [engaged in conversation, relaxed, focused, active].

Their body language suggests they might be [performing an activity: talking, working, reading, walking, exercising], and they are interacting with [objects they are holding or using: a smartphone, book, cane, laptop, sports equipment]. These interactions imply they are [specific activity: browsing the internet, reading a book, navigating their environment, working on a computer, playing a sport].

Physical characteristics of the individual(s) include [skin tone, skin color, a guess at there race even if that isn’t allways right, height, body type: slender, athletic, average build, muscular, petite]. These features contribute to their overall appearance in the image.

The background of the image features [detailed description of surroundings: architectural elements like buildings or furniture, natural elements like trees or water, interior details like room layout or decorations]. This provides context for the scene, indicating whether it is set indoors or outdoors, in an urban or natural environment.

Lighting in the image is [type of lighting: bright, dim, natural, artificial], which creates [effects: shadows, highlights, soft illumination] on their features and the surroundings, adding depth and mood to the scene.

Overall, the atmosphere of the image feels [describe the mood: calm, energetic, lively, serene, bustling], and the individual(s) appear [describe their demeanor: focused, engaged, happy, contemplative, active]. Additional observations include [any unique details or context that enhance understanding, such as weather conditions, time of day, cultural elements].*

Usage Example:

*"In the image, there is a woman standing in a sunlit park. She appears to be in her early thirties, with long, wavy brunette hair that cascades over her shoulders. She is wearing a light blue summer dress with floral patterns and a pair of white sandals, giving her a relaxed and cheerful appearance. Her facial expression is joyful, with a bright smile and sparkling brown eyes framed by subtle makeup. She stands upright with a relaxed posture, holding a red umbrella in one hand and a wicker basket in the other, suggesting she might be preparing for a picnic.

Her skin tone is fair, and she has a slender build. The background features lush green trees, blooming flowers, and a paved walking path, indicating a peaceful outdoor setting. The natural sunlight casts soft shadows, enhancing the vibrant colors of the scene. Overall, the mood of the image is serene and happy, with the woman appearing content and enjoying a beautiful day in the park."

Extra, extra read-all-about-it!
This, is a cool list of voice commands and if you made it here, then thanks please give me a follow and share us with your friends, we have a Facebook group too called AI For The Blind, come join us there for more content.
Thanks, Shawn:

Here is a Voice Command Guide for AI Image Descriptions:**

  1. ho’s in the Picture?
    Say: "Who’s in the image?"
    Example Response: "There’s a young woman with short curly hair wearing a red jacket."

  2. What Are They Doing?
    Say: "What are they doing?"
    Example Response: "She’s walking her dog in a park, holding the leash in one hand and a coffee cup in the other."

  3. Where Are They?
    Say: "Where is this happening?"
    Example Response: "It’s an outdoor park with tall trees and a paved walking path."

  4. How’s the Lighting?
    Say: "What’s the lighting like?"
    Example Response: "The lighting is natural with bright sunlight, casting light shadows."

  5. What’s the Mood?
    Say: "How does the scene feel?"
    Example Response: "It feels calm and peaceful, with the woman looking relaxed as she walks."

  6. Detailed Description:
    Say: "Give me all the details."
    Example Response: "There’s a woman in her late twenties walking her dog in a sunny park. She has short, curly black hair and is wearing a bright red jacket over a casual white t-shirt and jeans. The park is spacious with tall oak trees, and there’s a paved path she’s walking on. In one hand, she’s holding a leash attached to a golden retriever, and in the other, a coffee cup. Sunlight filters through the trees, creating soft shadows. The overall feeling is peaceful and easygoing, like a quiet Sunday morning."

  7. Get Creative
    Say: "What’s something unique in the scene?"
    Example Response: "There’s a hot air balloon in the distance, drifting through the sky, adding a playful touch to the serene scene."

  8. Zoom in on Details
    Say: "Focus on a specific detail."
    Example Response: "Zooming in on the woman’s jacket, you can see it has a subtle floral pattern, and the golden retriever’s fur looks soft and shiny in the sunlight."

  9. What’s the Weather Like?
    Say: "What’s the weather?"
    Example Response: "The weather looks cool and breezy, with clear skies and just a few clouds drifting by."

  10. Full Story Mode
    Say: "Tell me a story about this image."
    Example Response: "A young woman strolls through the park on a bright, crisp morning. The soft rustling of leaves fills the air as her golden retriever trots happily by her side. A hot air balloon floats in the sky, its vibrant colors contrasting the clear blue. She takes a sip from her coffee cup, a moment of calm in an otherwise busy day. The sun’s warmth on her face matches the smile she wears as she watches her dog tug playfully at the leash. It’s a perfect autumn day."

Support AI For The Blind. by contributing to their tip jar: https://tips.pinecast.com/jar/wespeak

This podcast is powered by Pinecast.

Lesson 2 more basics

by

Just speaking as an everyday guy who’s an audible learner. Some people are visual, some are tactile, but I learn a lot faster when someone explains things to me or reads me the specifics. I know AI can sometimes be too long-winded—I feel that! So, I always try to keep it fun and lighthearted while learning something new. Mixing different approaches can lead to some pretty cool results!

For my podcast, all I’m doing is writing a text script. Then, me and AI tweak it a bit—sometimes I do more of the tweaking, sometimes it does. After that, I record it using Eleven Labs voice and post it to Pinecast. It’s so easy; anyone could do this! I might throw in some music and sound effects, but nothing special.

But hey, sometimes the content can get a bit boring, and it’s way faster to listen to JAWS or read on a braille display. So, don’t forget to check out the transcript in the description!

If you’re in this group trying to figure out what to do tonight, here are two fun options:

  1. If you’re new to using AI, ask it the one thing you’ve always wanted to know. I have no idea what your question is, but I know you’ll get an amazing response. I test this theory all the time to make sure I’m bringing you good content!

  2. If you’re familiar with AI and using any AI app—on any device, platform, or website—ask it to teach you something cool tonight, in simple, casual language.

Have fun with it! Share what you learn in the comments on this post—I will too!

Support AI For The Blind. by contributing to their tip jar: https://tips.pinecast.com/jar/wespeak

This podcast is powered by Pinecast.