Tag Archives: images

AI text in images just keeps getting better

Leave a reply

One of the biggest challenges with AI image generation is text. A new model, Ideogram 3.0 out of a Toronto startup, seems to have cracked the code. I wanted to try it out and so here were my two free prompts and their responses:

Prompt: Create an ad for a blog titled ‘Daily-Ink’ by David Truss.
The blog is about daily musings, education, technology, and the future, and the ad should look like a movie poster

Prompt: Create an ad for a blog titled ‘Daily-Ink’ by David Truss.
The byline is, “ Writing is my artistic expression. My keyboard is my brush. Words are my medium. My blog is my canvas. And committing to writing daily makes me feel like an artist.”

While the second, far more wordy prompt was less accurate, I can say that just 3 short months ago no AI image model would have come close to this. Now, this is coming out of a startup, not even one of the big players.

I didn’t even play with the styles and options, or suggest these in my prompts.

As someone who creates AI images almost daily, I can say that there has been a lot of frustration around trying to include text… but that now seems to be a short-lived complaint. We are on a very fast track to this being a non-issue across almost all tools.

—

Side note: The word that keeps coming to mind for me is convergence. That would be my word for 2025. Everything is coming together, images, text, voice, robotics, all moving us closer and closer to a world where ‘better’ happens almost daily.

Morality police

Leave a reply

I have regularly created AI images to go with my blog posts since June, 2022. I try not to spend too much time creating them because I’d rather be writing blog posts than image prompts. But sometimes I try to create images and they just don’t convey what I want them to, or they come across as a bit too much in the uncanny valley, feeling unnatural. That happened with my post image 4 days ago, and I used the image anyway, because I was pressed for time.

(Look carefully at this image and you’ll see a lot wrong with it.)

I made 5 or 6 attempts to adjust my prompt, but still kept getting bad results, so I made do with the only one that resembled what I wanted.

And then for the past couple days I had a different challenge. I don’t know if it’s because of using the version of Bing’s Copilot that is associated with my school account, but my attempts to create images were blocked.

And:

However, Grok 3, a much less restricted AI, had no problem creating these images for me:

And:

I’m a little bothered by the idea that I am being limited by an AI in using these image prompts. The first one is social commentary, the second one, while a ‘hot topic’, certainly isn’t worthy of being restricted.

It begs the question, who are the morality police deciding what we can and cannot use AI to draw? the reality is that there are tools out there that have no filters and can create any image you want, no matter how tasteless or inappropriate they are, and I’m not sure that’s ideal… but neither is being prevented from making images like the ones I requested. What is it about these images requests that make them inappropriate?

I get that this is a small issue in comparison to what’s happening in the US right now. The morality police are in full force there with one group, the Christian far right, using the influence they have in the White House to impose their morality on others. This is a far greater concern than restrictions to image prompts in AI… but these are both concerns on the same continuum.

Who decides? Why do they get to decide? What are the justifications for their decisions?

It seems to me that the moral decisions being made recently have not been made by the right people asking the right questions… and it concerns me greatly that people are imposing their morals on others in ways that limit our choices and our freedoms.

Who gets to be the morality police? And why?

Persistence and Patience

Leave a reply

I like images and graphics that make you think, and especially ones that are motivating. But sometimes for the sake of an image trying to tell a story, another narrative can either be missed or take over from the intended message. That’s something that immediately occurred to me when I saw this ‘inspirational’ image.

To me, the intended message is that we always need to keep learning, but it suggests a uniformity of practice and process that’s just plain wrong. To the person who posted it, Steven Bartlett, the message was about relentless consistency. He said,

For anyone frustrated with how long something is taking you right now…

Remind yourself of this.

Relentless consistency is usually the answer. I’m not talking about a sprint, I’m talking multi-decade.

What’s one thing you do to remain consistent?

But that uniformity between LEARN and APPLY in the image really bugs me no matter what the intended message. While other commenters mentioned positive interpretations like, ‘Consistency is key’, and ‘Focus on the long game’, I commented:

I think my greatest learning is that application always takes longer than you think. Persistence needs to be tempered with patience.

I wish learning was that easy. I wish I could apply everything I learned so consistently and effortlessly. I can’t. And I don’t think anyone can. There are hours of practice, there are mistakes made, detours and distractions. There is never the consistency and uniformity off application of learning seen in the image.

Is the message of relentless consistency over a long period of time important? Absolutely! But I really think this image misses the mark in sharing what relentless consistency looks like. The hardest part of relentless consistency is when application of learning does not go smoothly and application of what you’ve learned takes months to accomplish. And yes, sure that also often means more learning, but the grunt work of making things work can often be the times when consistency really matters, and isn’t so evenly worked through as suggested in the image.

Persistence needs to be tempered with patience. If constant results and application of learning are expected, this will lead to disappointment and frustration… neither of which inspires consistency.