I Dove Back into AI and Returned to Windows

The one downside of leaving Windows for Mac is being unable to render AI images locally – at least not with the degree of flexibility available on Windows. Most apps and models are Windows-only. The only Mac app I’m familiar with is called Diffusion Bee, but support for it is lackluster and its UI is unintuitive. Consequently, I’ve had to relegate myself to web-based services. Unfortunately, the best AI model I’ve found isn’t free or NSFW, so I’ve had to be extra-creative and think outside the box to come up with text prompts that won’t return ToS alerts. Nevertheless, it will not generate nudity, and provocative clothing is a no-no.

The model I’m referring to is Google’s Imagen 4, and it’s available on Krea.ai with a subscription. Not even Flux – a widely popular open-source model – matches its visual fidelity or prompt adherence.

Thankfully, a close family friend – we’ve known each other since High School – gifted me a one-year membership to Krea’s Max plan for my birthday last month. Suffice it to say, I went a little nuts, and have lots of new content to share. Since Krea doesn’t allow NSFW content, I wound up returning to Windows so I could use Fooocus to inpaint nudity offline. I love my new iMac, but again, it’s not well-suited for AI, so I re-purposed it for video editing.

In other news, I re-arranged my Galleries. My 3D and AI art now have their own menu structures, and I’ve created separate pages for my AI Enhanced and AI Generated work.

With all of that in mind, one thing I discovered about Imagen 4 is that it knows who Michael Myers is. He’s my favorite Horror movie villain, and I created a new gallery to showcase his exploits with ten images to start.

There are seven new one-offs on my AI Generated gallery: They’re called Strangled Attorney, Impossible Demands, Strangled Streamer, Cop Killer, Behind Glass, Case Dismissed, and Hitman’s Prerogative. I also created my first – and only – multi-panel AI comic, called Whistleblower.

Finally, I experimented with the new Wan 2.5 text-to-video model. You can read about that and watch my test clips on my new AI Videos page.

Switching to Mac, Putting 3D on Hold

Switching to Mac

I’ve used Windows ever since the first version came out in 1985, and built my current PC four years ago. The most expensive component was my RTX 3090 at $1750. I’ve never been proud of having paid that much, I’ve never liked its inefficient energy usage, and I’m tired of it sounding like a jet engine when rendering.

As GPU prices have continued rising, I’ve been telling myself that, if the market hasn’t settled by the time I’m ready to upgrade in the next few years, then I’m switching to Mac. nVidia’s last event, in which they announced their new 50x series and revealed the $2k MSRP for the 5090, didn’t help. IMO, there is no good reason why a single component should cost nearly as much as a down payment on a car. Bottom line, I am very displeased with the current state of the PC market, and firmly believe my current build will be my last.

I bought my M1 MacBook Air when Apple unveiled their own silicon in 2020. I wanted to try Apple’s ecosystem, and the M1 chip felt like the ideal entry point. Five years later, there are still a few quirks about MacOS that I continue wrestling with thanks to decades-long muscle memory from Windows, but my overall experience has been more positive than negative. “It just… works,” is not hyperbole. In contrast, my current PC failed to post the first time after building it, and I’m still bitter about the few hours I spent trouble-shooting the problem. Watching a tech guru on YouTube experience a similar issue a few months ago after building a new PC for a client brought back that unpleasant memory. I’m not looking forward to the risk of that happening again.

As a visually oriented person, I’m also deeply influenced by design language and aesthetics. On those two points alone, Apple’s ecosystem has always strongly appealed to me, much moreso than Windows. Unfortunately, my needs as a 3D artist have kept me anchored to Windows. Welp, that ends today.

After extensive research and contemplation, I pulled the trigger on a new silver M4 iMac last week, taking advantage of an 11% discount on Amazon for a cost of $1695. It includes 24 GB of unified memory and a 512 GB SSD. I also bought a 1TB Samsung T7 SSD.

I’ve wanted an iMac ever since the first Intel-based 27″ model came out in 2009. They’re gorgeous machines, and I’ve been envious of anyone I learned owned one.

Putting 3D on Hold

Thanks to a series of marketing blunders in recent years, and their failed attempt at their own brand of AI, Daz3D have left many artists, including me, with the impression that they can’t get their shit together, and are just tossing ideas at the wall to see what sticks. To make matters worse, they still haven’t managed to release an Apple silicon version of Daz Studio. Therefore, I’m putting 3D art on the backburner, and will continue experimenting with AI.

New AI Enhanced Art: “Secretary Grabbed”

My latest piece was inspired by an AI experiment an artist recently shared on the AI Art section of a newly opened forum called Renderunto.com. Like me, he used to shun AI, and then found himself toying with it over a year ago. Unlike me, he has since transitioned completely away from Daz, and now works solely with AI. His experiment is titled Grabbing the secretary if you want to check it out. That section of the board is accessible without registering.

His experiment involved using nothing but AI and GIMP to create a secretary trapped in a hand. He wound up having to create two separate images – the hand and the secretary – composite them in GIMP, and then use the composite as the base image in Forge.

My experience with AI and the challenges I’ve failed to overcome using it by itself have led me to conclude that, for my needs, such complex scenes must start with a fully posed, lit, and rendered base image. It’s the only way to prevent unsightly AI deformities and maintain full control over lighting and camera angles.

Pressing Pause on AI

My creative output has been virtually non-existent since January because I spend more time experimenting with AI and trying in vain to produce what I want. In light of my stagnation, and thanks to some great advice from a fellow artist, I’m pressing Pause on AI until it reaches a level of maturity that’s better suited for my needs.