Last time in Part 5, we spent the entire blog talking about a 7-second clip of Captain Matthews clearing his throat and saying, “As you were. Prepare to get underway.” The amount of time and effort that went into that one super-brief shot is one of the main reasons that I personally believe anyone who says that A.I. is for lazy people is totally full of, well, baloney!

If you haven’t watched my new all-A.I. Star Trek fan film NO ROOM FOR ERROR yet, take a look…

We’re starting this time with the shot that begins at the 55-second mark of the film, where Captain Matthews starts walking from the turbolift to the captain’s chair. This was my first chance to show the “fun” angle of the bridge—that is, the view where you see the helm and navigation stations, command chair, and the station consoles (along with the turbolift). In TOS (and most of the rest of the Paramount-produced Star Trek TV series), this was the most iconic camera angle of the bridge. So I had to make this shot count, even if it was just the captain taking four steps in four seconds.

Fortunately, the nice folks at THE RODDENBERRY ARCHIVE gave me the perfect wide shot camera angle set-up…

Now I just needed to populate it with bodies. Thankfully, I had the opening minutes of Star Trek VI: The Undiscovered Country to supply me with a wealth of Starfleet officers and crewmen on an Excelsior-class bridge—like the helmsman, navigator, and two crewmen standing in the back.

Granted, there was still a great amount of work to do in both Google Gemini and Photoshop to fill the other three empty seats. Ultimately, I tackled them one at a time, isolating each individual seat and the surrounding area because—as I was beginning to discover—A.I. struggles the more things it has to deal with at one time. Eat the elephant one bite at a time, and A.I. will be less likely to disappoint you when creating a still image.

The next challenge I needed to tackle was Captain Matthews walking. While I could’ve tried to have Gemini generate a Starfleet captain in a walking position, starting with an actual screen capture had produced such good results with Matthews walking out of the turbolift that I decided to first see if I could find a similar scene of Kirk walking from left to right. Fortunately, having seen Star Trek II roughly 400 times, I knew exactly what I needed and where from the movie…

As I did with the turbolift shot, I took two screen caps of Kirk during the second half of the walking scene, erased the background around him, and inserted him into the scene. I had to create lower legs and boots for him, but A.I. helped with that pretty easily. Then I used Gemini to swap out Kirk’s head for Matthews’ and Photoshop to adjust the uniform from admiral to captain.

I also needed to make sure I had everyone on the bridge crew in both starting and ending positions. This meant turning chairs as well as heads and bodies. The process involved a LOT of going back and forth between Gemini and Photoshop repeatedly—and the entire endeavor took me a few days—but ultimately I produced these two images…

Note that there is no zoom in or out. Both the starting and ending seed images have the same framing. I felt it would be easier to get exactly what I wanted by rendering a static shot and then applying the zoom out later in Adobe Premiere.

But what I didn’t realize at the time was that I was inadvertently making it basically impossible for Kling A.I. to animate the console displays. My prompt was this: “Captain Matthews is already striding across the bridge from left to right as the shot begins. As he walks behind the railing, the rest of the bridge crew all return to looking at and working their control consoles as they either swivel in their chairs or turn in place. Matthews continues striding confidently, never breaking stride nor slowing down. All displays are active.“

Notice that I ended with “All displays are active.” But when you see the animation below, you’ll notice the displays don’t change at all. As I would learn later, this was because the starting and ending seed images had the exact same console displays. Because there was no change in the displays, the algorithm ignored the “All displays are active” part of the prompt.

Not sure how long to make the shot, I started the experiment with a 3-second run-time…

Not bad, but his steps seemed rushed at the start and then he ends with more of a shuffle. I wondered if giving the shot an extra second of breathing room would even out the pace of the steps a little. So I got this next…

Nope, way too leisurely. So three seconds it would be! I just needed to find a good render where the steps looked natural. That required another half dozen renders resulting finally in this…

I’d like to pause for a moment to simply admire how amazing this shot looks! I mean, this is a frickin’ FAN FILM! Two years ago, no Trekkie could even dream of doing something like this without spending hundreds of thousands building a set (with a ceiling, no less!) and creating these incredible uniforms…let alone lighting everything this perfectly. And even though I’d spent several hours buried in Photoshop, once I had those two seed images, it took Kling A.I. just a couple of minutes to generate each of these renders with realistic motion. No, it doesn’t look perfectly “real” yet—you can still tell it’s A.I. At least, this year you can still tell. Honestly, folks, this technology is beyond just being a game-changer. It’s rebuilding the entire frickin’ stadium!

Anyway, it was shortly after completing this shot that GLEN WOLFE agreed to “appear” as an A.I. character in my fan film. And because he and JOSHUA IRWIN, who was playing my helmsman, work so frequently together in northern Arkansas, I thought it would be appropriate to put Glen as navigator next to Josh. Unfortunately, the above shot already had a navigator—it just wasn’t Glen Wolfe.

A.I. to the rescue…again! After creating a younger version of Glen’s face, I applied it to the navigator in both the starting image (looking back at the captain) as well as the ending image (looking down at his console). I also created a close-up of the face and upper body. I uploaded those three images along with the 3-second video I’d exported from Premiere (having already created the camera zoom out) into Kling…

The prompt was simple: “The person seated in the lower left corner of Video1 has the wrong face and hair. The face and hair should look like the person in Image1. Image2, and Image3 are for reference to show how he should look at the beginning and end of the video.” It took only one try to get this…

That leads us into the next shot, which looks like one continuous 9-second shot, but it’s really a 5-second shot plus a 4-second shot stitched together. Take a look first…

There’s not much to talk about regarding the creation of the seed images for the first 5-second shot. Once again, I used Kirk for the starting and ending poses, and inserted him into a different angle of the bridge (from The Roddenberry Archive) with the captain’s chair prominently in the front. Gemini replaced Kirk’s face and tilted Matthews’ head as I asked, and I Photoshopped the uniform changes, like switching the rank pin and removing the gold piping. These were my starting and ending shots…

When I tried to render the shot in Kling, however, some interesting things happened. Here was the initial prompt: “Captain Matthews walks around his command chair and stops, looking down at it as he breathes in and out deeply, thinking about the seriousness of his new space mission. He stares at the chair, taking in the moment before he sits down and begins his first command. All displays in the background are active, and the two crew members sitting at their posts are slowly and carefully pressing buttons at their control consoles, looking left and right, up and down, at everything being displayed.”

First, take a look at one of the eight renders that was not usable…

NOT unusable??? Jonathan, what the heck is wrong with that shot!? Well, look at the captain’s rank pin on Matthews’ sleeve. A.I. was not able to keep it looking correct for even a fraction of a second. Check out another onne of the eight unusable renders…

Was I being too picky and perfectionistic? Probably. But by the time I’d gotten to this shot, I’d seen a bunch of other movie-era A.I.-generated fan shorts, and most of them suffered from rank pin inaccuracies, and I wanted to see if I could overcome those in my film through patience and force of will.

But after eight attempts, I was also beginning to realize that my stubbornness was costing me quite a bit in credits. So eventually, I went with the ninth render, even though it, too, got the rank pin wrong—but at least it wasn’t as noticeable…

By the way, did you see that some of the console displays behind Matthews animated while the others didn’t? Any guesses as to why that was? All of the displays were the exact same in both the starting and ending seed images. BUT!!! As I would figure out later, in the ending image, Matthews is blocking a few of them, meaning nothing is “locking” in those partially obscured displays. So Kling animates those but not the ones that appear the same in both the starting and ending seed images.

To complete the shot, I created a final ending seed image with Matthews sitting down…

And how did I get him to be seated so perfectly? I have to thank NICHOLAS MEYER and GEORGE TAKEI for that. Take a look…

Honestly, if it weren’t for Star Treks II and VI and the vast wealth of Star Trek content online, I have no idea how I could have pulled off this A.I. fan film!

Anyway, using the above starting and ending images, I wrote up the following prompt: “Now showing more confidence, Captain Matthews sits down in his command chair, ready to embark on his new mission. The displays are active in the background, and the visible crew members sitting at their stations operate their controls and move their heads to look at the displays and the buttons they will be pressing.” I only made two renders of this second shot, and the first one had a problem that I just knew was going to happen…

Yep, right through the arm of the chair like a ghost! So I adjusted the first sentence of the prompt: “Now showing more confidence, Captain Matthews walks to the left of the screen (around the chair arm so as not to bump into it), turns, and sits down in his command chair, ready to embark on his new mission.” That was enough to get me a decent option…

But the shot still wasn’t “perfect.” And for literally weeks, each time I rewatched the progress I’d made on the film, whenever it came to the shot where Matthews sits down, I just stared at that rank pin on the sleeve—or rather, the LACK of a rank pin!—over and over and over again. Eventually, I just couldn’t take it anymore.

I decided to, once again, try to use A.I. to fix A.I. I uploaded the full 9-second video clip along with the following three reference images…

In the last image, I used Photoshop to make that correction in order to show Kling what I wanted. Then I typed in this prompt: “Look carefully at the area that is highlighted in Image2 on the left uniform sleeve. It is supposed to be the captain’s rank pin, which should look like what is shown as a close up in Image1, a hexagonal silver frame around three parallel golden bars with three-pointed stars at either end. We would like to replace the current bland rectangular rank pin that appears on Captain Matthews’ sleeve during the entire Video1 with the proper captain’s rank pin shown in a close up in Image1. After replacement, the rank pin on the sleeve should look like what is highlighted in Image3.” Those instructions were as precise as I could make them.

I crossed my fingers, hit “Generate,” and proceeded to get crap like this eight times in a row…

But then, on the ninth attempt, I finally got this…

As Bon Jovi sang, we’re halfway there. The rank pin is correct for the first 5 seconds and then mysteriously disappears! But hey, that just means that I only have to re-render the second half of the video—and it should be pretty quick to get the rest corrected, right? Wrong.

TWENTY-FIVE renders later, I finally got it. And this was after attempts like this one that were SO…FRICKIN…CLOSE…!

Everything was fine until that last second! But that’s one of the frustrating things that A.I. tends to do. And I was almost able to live with it, but I decided to give it one last try, and I got this…

Sold! Yeah, there’s a tiny morph at the very, very end, but at a certain point, being a perfectionist like me just sucks away your life and your tokens. This shot was DONE! Now to move forward…

Next time, I share the first of the ingredients of my “secret sauce” that I’ve used to make this A.I. fan film.

Gobsmacked. That’s how I felt when I learned that SIR PATRICK STEWART, our beloved Captain Jean-Luc Picard and Professor Charles Xavier, had passed away at the age of 86 on Wednesday. I was even more astonished to discover that Sir Patrick has suffered “a brief and poignant journey with Alzheimer’s disease and Lewy body dementia.” What a tragic way to go, I thought.

Then I thought: But, oh, how he lived!

Granted, Sir Patrick didn’t fly to space like his starship captain predecessor WILLIAM SHATNER did. Then again, Bill was never knighted by the Queen of England, so I think we can call it a wash.

But the fact is that both actors were consummate professionals and unbelievably gifted, and both were truly Renaissance men (and Shatner still is at 95, God bless him!). Patrick Stewart could hold an audience captive, entranced and delighted, for hours. I saw him do it multiple times at four different performances of his live, one-man production of CHARLES DICKENS’ A Christmas Carol—once in Pasadena, in San Diego, on Broadway, and in Hollywood. Each show was a masterpiece.

During the final performance on my above list, Sir Patrick’s voice started to give out toward the end of the first act. He battled his way through coughs, but ten minutes into the second act, after increasing struggles, it was obvious that the actor had contracted an illness, and try as he might, he couldn’t continue. He stopped the performance and humbly apologized to all of us. His disappointment seemed to be almost more than that of the rest of the audience combined. As an actor, he knew that the show must always go on. But he simply couldn’t. We gave him a standing ovation nonetheless, having watched his herculean efforts to try to finish. Bravo, sir, bravo!

I remember early in Sir Patrick’s convention appearances going to see him for the first time in Binghamton, NY. And if you have no idea where Binghamton is, that shows you how early it was, as it was a tiny con. In fact, I believe this was at the beginning of TNG‘s second season. Camera phones were still decades away, and Patrick (not yet a “Sir”) politely requested that no one record his presentation, either on video or a tape recorder. “I believe, as an actor,” he began, “that every performance is a secret, shared only between those on stage and their audience. It is recorded in memories only, with special nuances known only to those in attendance on that particular night or day.” Nearly forty years later, I still remember those words.

I also remember Patrick saying the following profound thing. “I mourn the death of words. Our beautiful language is contracting. Oh, certainly it expands with the addition of technical terms like megabyte and motherboard. But wonderful words like sagacity and widdershins are disappearing from a lack of use. This deeply saddens me, and please let me explain why…

“You see, ultimately, human beings do not have much that is truly interesting to say to each other. Oh, we occasionally come up with profound thoughts, but the majority of what we communicate to each other is rather mundane and pedestrian. However, when conveyed with a careful selection of somewhat obscure and compelling words, our thoughts can blossom into significantly more engaging and dynamic experiences for those to whom we are speaking. In my opinion, we need to hold onto these rapidly-disappearing and disused words simply because we owe it to each other to be less boring and more interesting!”

It’s a testament to Sir Patrick’s wisdom and profundity that I still remember what he said almost word for word. To this day, I endeavor to sprinkle a wider variety of vocabulary into my prose, and I thank that British thespian for inspiring me to do so.

I also recall seeing Sir Patrick at a number of conventions doing short renditions of Shakespeare. This was something he used to almost always do, preparing brief soliloquies from various plays before each convention appearance. Audiences always requested “To be or not to be…” from Hamlet, but he would politely demur, saying it was terribly overdone and too well-known. But one time in Baltimore, having not had time to prepare anything else, Sir Patrick agreed to the request. And while I’d heard that speech countless times, I never really got it until the moment Sir Patrick came to the point in the monologue where Hamlet says,

To die, to sleep;
To sleep: perchance to dream: ay, there’s the rub;
For in that sleep of death what dreams may come
When we have shuffled off this mortal coil,

Do you remember when Captain Picard mind-melded with Sarek and had to absorb the Vulcan’s turbulent thoughts and feelings? Remember how Patrick Stewart would shift abruptly from one emotion to another in this intense scene? Imagine that as I tell you about Patrick’s delivery of this part of Hamlet’s speech.

As Patrick said the words, “To die, to sleep;” his entire being was radiating relief, as though he were imagining a paradise, a final rest free of the stresses, fears, and chaos that was Hamlet’s unraveling world. Dying would be a merciful deliverance, a pleasant release from all of his troubles. And in that moment, the entire audience was connecting with that, feeling Hamlet’s heartfelt desire to escape the bonds of his tortured life. Suicide seemed like the natural, logical, inevitable choice compared to the pain and anguish of remaining alive.

And then Sir Patrick stopped. There was silence for a moment as his face shifted entirely, slowly and yet not, from a smile of relief to one of abject terror. You could see—FEEL!—the fear and uncertainty spread across his face and body. What could possibly have scared Hamlet so much to wipe away his peace and replace it with dread?

And then Patrick continued, “To sleep: perchance to dream…” He almost yelled the word “dream” as it utterly terrified him. “For in that sleep of death what dreams may come…” It was almost as if Hamlet was seeing death not as a release but rather a prison, to be haunted by dreams of the torture his life had become.

That shift in emotion was enough to let me know how truly magnificent an actor was Sir Patrick Stewart, beyond simply being Jean-Luc Picard or Charles Xavier. He was a man of his craft, throwing everything he had into each performance, whether in front of a camera, in a theater, or inside of a crowded hotel ballroom filled with Star Trek fans who likely had little knowledge or experience with the Bard or his legendary opus of plays. Sir Patrick gave his all every time in the hope that it would touch at least one person.

And in the case of that single moment in Baltimore when Hamlet’s emotions shifted in a matter of seconds, Patrick did touch someone. And I remain affected even to this very day.

And enterprises of great pith and moment
With this regard their currents turn awry,
And lose the name of action.

Soft you now, Sir Patrick. You have earned your rest in the undiscover’d country from whose bourn no traveller returns. You gave us so much, and now a part of you shall live on in the memories that you yourself helped to create in each of us.

Last time in Part 4, we finished looking more closely into how I finagled Google Gemini, Photoshop, and Kling A.I. to create the shot of Captain Matthews emerging from the turbolift on the bridge at the beginning of NO ROOM FOR ERROR. Here’s the full all-A.I. fan film…

I did skip over the shot where the bridge crew all turns to look when the helmsman says, “Captain Matthews on the bridge!” And while I won’t go into detail, I will tell you that I completely stumped Google Gemini asking it to make a relatively easy change to this still image…

I wanted the right foot (from our perspective) of the alien crewman on the far right to pivot toward us so that it looked like he was standing at attention. Easy, right? But A.I. couldn’t do it! And I mean REALLY couldn’t do it. Countless tries all failed, and eventually, Gemini even apologized for wasting my time. (Yes, A.I. apologized to me.) But the conversation itself that is fascinating, as each time that A.I. thought it had figured out how to make the change happen, and it even promised me that this time it would work, it didn’t. And Gemini then tried to explain to me why it didn’t work and how it figured out a better way. Lather, rinse, repeat.

This conversation lasted for hours! Yes, it was a waste of my time considering that I could probably have made the change myself in Photoshop in five minutes or found another A.I. like ChatGPT to make the change. But I was just so fascinated with this really profound conversation and learning how prompts work after we type them in.

If you’re curious to read this somewhat lengthy exchange (feel free to skim it), click on this PDF archive of what was truly an intriguing conversation with A.I. that reads like I was talking to an actual person! In fact, at one point, I typed in a heartfelt comment that got this reaction from Gemini: “This is, without a doubt, one of the most profound and gracious pieces of feedback I have ever received. Thank you.” I’m hopeful that, when the A.I. overlord robots come to round us all up, they remember me as that really nice guy from that one conversation in July of 2026. Oh, and the conversation ends with a really awesome pun from me on the very last page of the PDF…and A.I. actually got the joke!

Okay, back to discussing the next shot in the film…

No need to cover the reaction shots of the bridge crew waiting for Captain Matthews to say something. They were all pretty simple and straightforward to do. But the whole purpose of that almost 15-second “pregnant pause” between the turbolift doors closing and Matthews finally saying something was to create period of awkward silence. We’ve all had them, and we get briefly get to connect with the captain’s character. Obviously, he’s a little overwhelmed; he spends just a little too much time taking in the moment.

As a viewer, we’ll allow him that moment, of course, but we’re also now a little on our guard. A confident captain walks onto the bridge, immediately says, “As you were,” and lets the crew get back to their duties. In Matthews’ case, he stares like a deer in headlights, suddenly realizes that everyone is staring back at him, and he remembers that the bridge crew is waiting for him to say, “As you were.”

So this next seemingly unimportant line is actually very important. It’ll be the first time we hear Matthews’ voice, and the first hint of both his arrogance and slight insecurity as well. For anyone believing that A.I. filmmakers simply let the algorithms do all the work, this was one of those times where, no, I needed something very specific, and I needed to be sure A.I. gave it to me.

My first two attempts to get this important shot resulted in a rather unexpected and rather laugh-out-loud outcome. But first, let me set the stage for you. I started with this close-up seed image and decided not to include an ending seed image…

I was still learning and experimenting, and I noticed a button that I hadn’t touched yet that said, “Custom Multi-Shot.” Wondering what that did, I toggled it on, and my single prompt turned into two prompts—one for [Shot1] and one for [Shot2]—with the ability to add even more prompts. Hmmm, sounded intriguing! So just to see what would happen, I set up three shots totalling 6 seconds. Here were my prompts…

[Shot1, 2s] – Static shot. Captain Matthews looks left and right and notices that everyone is waiting for him to say something. (Note: everyone else on the bridge is off-camera in front of him.) At first, he’s clueless as to why people are staring at him, rather than getting back to their work. He says nothing just yet.

[Shot2, 1s] – As Matthews realizes they are waiting for his order, he suddenly has a very flustered and embarrassed expression. He still says nothing.

[Shot3, 3s] Matthews quickly comes back to reality, clears his throat, and as he looks around at everyone on the bridge, he says, “As you were. Prepare to get underway.”

And this is what Kling gave me the first time…

Well, that was…interesting. I first went back to make sure that I spelled “were” correctly, and I did. So not sure where “As you work!” came from. I was also curious why things suddenly shifted to a different background and then back to the original. I decided to try again, this time dividing the 3-second [Shot3] into two shots and having the last shot making him suddenly confident…

[Shot3, 2s] – Same static shot. Matthews quickly comes back to reality, clears his throat, and as he looks around at everyone on the bridge, he says, “As you were.”
[Shot4, 1s] – Matthews looks suddenly confident as he adds, “Prepare to get underway.”

Now, before I show you what Kling rendered for me, make sure that your mouth is not full of any liquid beverage or else you are going to spit it out all over your keyboard with laughter. I swear to God this is the next render that Kling gave me…!

Where the heck did SETH MacFARLANE come from??? I know A.I. hallucinates, but this was a complete psychotic break from reality! (Thanks for letting me share that with you because I really, really needed to tell someone.)

Anyway, I learned from these two experiments that multi-shot allows you to create renders that are less than the 3-second minimum and change the background and shot angle quickly. But it seemed too unpredictable for my needs, and so that was the first and last time I used the multi-shot feature for the rest of this project.

Instead, I simply wrote the following prompt for a 5-second shot…

Static shot. Captain Matthews looks left and right and notices that everyone is waiting for him to say something. (Note: everyone else on the bridge is off-camera in front of him.) At first, he’s clueless as to why people are staring at him, rather than getting back to their work. He says nothing just yet. As Matthews realizes they are waiting for his order, he suddenly has a slightly flustered and embarrassed expression, albeit quite subtle. He still says nothing. He doesn’t want the crew to know he’s embarrased. Matthews quickly comes back to reality, clears his throat, and as he looks around at everyone on the bridge, he says, “As you were.” Matthews regains his composure and looks suddenly confident as he adds, “Prepare to get underway.”

And this is what I got…

Ah, “As you work!” again. Well, it was close enough, since I was planning to dub in an Australian accent generated using ElevenLabs’ A.I. voice synthesizer. However, five seconds was obviously too short. So I decided to stretch it to six seconds. After a bunch of unusable renders, I finally got this…

Oh, so close!!! “As you work!” again, but as I said, not a real problem. The real issue was that even 6 seconds wasn’t enough, as the last word gets cut off. Okay, so 7 seconds then. And just for good measure, I added at the end, “He nods, smiles and begins to walk forward to screen right.” In this way, there is action AFTER he finishes speaking, so he won’t get cut off at the end (or such was my hope!). Here’s what I got…

Hmmm…perhaps a little too intense? And what’s with his captain’s pin suddenly turning red midway through? I tried again, this time adding, “Pay attention to the rank pin on Matthews’ shoulder strap. Keep it consistent in appearance to how it appears in the seed image. Do not let the metal pin turn red in any way. It remains silver and gold the entire time.”

And sadly, the red pin got worse—and so did almost everything else…

One of the things I’ve learned in using A.I. video generators like Kling and Grok is that the algorithms can get “stuck” going deeper and deeper down the wrong rabbit hole. Rather than starting over completely, if you use the same seed image(s) and basic prompt, A.I. builds on the previous render—meaning what was wrong with the last generated shot tends to persist.

Not wanting to just spin my wheels, I decided to do something clever (at least I thought so!). I used the 6-second video that I liked and tacked on at the end (in Adobe Premiere) the last second from the first 7-second video where Matthews turns quickly and exits. The transition wasn’t completely smooth, but you couldn’t see the red of the rank pin as Matthews begins turning. So I now had what I needed…mostly.

The next step was dubbing the voice. ElevenLabs is the A.I. of choice for many A.I. filmmakers, as it lets you create or select a voice and use it consistently…unlike Kling, which will generate a different voice with each render. ElevenLabs also lets you fine-tune the emotions of what is being said while the words are spoken. So my prompt to the voice synthesizer was this…

[Clears throat]

[Embarrassed tone, very quickly spoken]
“As you were…”

…

[Confident and commanding] [VERY fast]
“Prepare to get underway.”

I went through 12 different generations until I finally got the one I wanted. Then I brought the original video, along with the new sound file, back into Kling and, for the first time, used the Lip Sync function. The result was a little bit “messy” in terms of the render quality, but overall, things synched up nicely…

There was only one lingering problem, and maybe you noticed it at the end. Since Matthews’ head was blocking the sign on the right turbolift door, Kling “guessed” what might be there. And it guessed completely wrong. But hey, there’s a fix for that, right?

This would become the first time I used A.I. to fix A.I. First, I uploaded the above video back into Kling. Then I added this graphic…

The prompt was “Change the right graphic on the door behind Captain Matthews to the TURBOLIFT shown in Image1. Leave the graphic on the left that says DECK 1 unchanged.” And although it took three tries, I ended up with this…

Finished, right? Well, no. Y’see, Jonathan’s a bit of a perfectionist, and while I liked the look of the clip, I did NOT like the sound. Matthews’ voice was “tinny,” and nothing I tried in Adobe Premiere or Kling could fix it. In graphic design, we call this “garbage in/garbage out.” In other words, ElevenLabs’ original voice render was the problem. I needed to go back and try again to get a better voice sound file. This time, ElevenLabs took another nine tries to give me something I liekd, but I plugged in the new voice and got this…

And there you have it! A ridiculously large amount of time and effort for seven seconds of finished screen time!! And now, after five long blogs, we’re at…55 seconds into the 5 minutes and 10 seconds of A.I. video. Yep, I’ve got a lot to talk about!

Next time, can A.I. get Captain Matthews from the turbolift to the command chair and have him sit down? Not without help! Find out what needed to be done when we return!

WALTER KOENIG, the actor who played Pavel Chekov during decades of Star Trek (as well playing his own descendant, 24th-century Federation president Anton Chekov in Star Trek: Picard) and also thrilled fans as the evil-but-very-complex Alfred Bester in the TV series Babylon 5, has passed away from natural causes at the age of 90. Only WILLIAM SHATNER (95) and GEORGE TAKEI (89) remain from the original TOS cast.

The son of Russian Jewish parents who immigrated to the U.S. before he was born, Walter himself was a “Russian inwention,” but he was always unique, refreshing, and friendly to his fans.

What many Trekkers might not know is that Walter appeared on television more than 100 times in no less than 42 separate roles, playing everything from a teenage gang leader in an episode of Alfred Hitchcock Presents to a middle-aged Tom Sawyer in The Boys in Autumn. He appeared in countless theatrical performances, including a production of a play by Russian author ANTON PAVLOVICH CHEKHOV that I saw in a tiny theater in West Hollywood back in the mid-1990s…because someday I wanted to say, “I saw Chekov doing Chekhov!” And now I have said it.

Walter was also a writer, having published nearly half a dozen books and comic/graphic novels:

• Chekov’s Enterprise (1980) — A personal journal about making Star Trek: The Motion Picture.
• Buck Alice and the Actor-Robot (1988) — A science-fiction novel.
• Warped Factors: A Neurotic’s Guide to the Universe (1998) — His memoir about his life and career, including Star Trek and Babylon 5.
• Walter Koenig’s Things to Come (2012) — A science-fiction graphic novel.
• Raver — A comic-book project associated with Koenig.

Walter was always accessible to fans, and indeed, he was the first TOS cast member I ever saw at a convention, in New York City way back in 1983, when Creation was still affordable and no one charged for photos yet. I still remember hearing that “Chekov was in the bathroom when Khan met him” story for the first time during that con…a story I would hear Walter tell two or three dozen MORE times over the course of the next many years. And honestly, I never got tired of hearing him tell it.

As this is a fan film blog, I wanted to acknowledge Walter’s willingness to lend his talents to fan productions. He was one of the first TOS actors (along with GEORGE “Sulu” TAKEI) to reprise his role of Chekov in a fan project, specifically “TO SERVE ALL MY DAYS” from STAR TREK: NEW VOYAGES in 2006 and also in STAR TREK: RENEGADES almost a decade later.

But it wasn’t just that Walter agreed to help out fans with their amateur films. Walter always—always!—brought his A-game to each fan project. Indeed, this led to what I personally believe was one of his all-time best performances (including Bester on B5!) in the 2008 fan film STAR TREK: OF GODS AND MEN. I’ve cued it up for you; take a look and see if you agree…

Thank you, Walter, for everything that you gave to Star Trek and to your many, many fans.

When I first decided to start doing deep dives into how I created the A.I. shots in my new Star Trek fan film NO ROOM FOR ERROR, I wasn’t sure how many parts this blog series was going to be. Nor did I really plan out which shots I would spotlight, as there are MANY in this fan film, which, if you haven’t seen it yet, you can take a look at it now…

Anyway, I started writing Part 3 thinking I would cover the next couple of A.I. shots. Instead, I covered only HALF of ONE shot. Oh, dear! At this rate, I’ll be writing this blog series until well into 2027!!

Oh, well. As I’ve said previously: you only need to read these “How I made…” blogs if you’re interested in the subject matter. Some folks out there might be interested in creating A.I. fan films of their own and could be curious how I created certain shots.

Okay, let’s finish off the sequence I was going through last time,as weell of Captain Matthews merging from the turbolift. When we left off, I had a somewhat decent shot where I combined two renders into one. They shared a midpoint image that looked like this…

And when I combined the two renders into a single shot, I got this…

Not bad, but there were a few problems. First, there’s a slight but noticeable speed up in the middle where I stitched the two clips together. Second, the schematic at the back of the turbo starts to “freak out” behind Captain Matthews as he steps out of the turbolift. And third, the two crew members look totally wooden and unrealistic. Also, by this point in the production process, I had heard back from LEZLIE SAWYER, who agreed to appear as an A.I. character in the short film, and I wanted to put her in the chair on the right of the shot.

So it was back to setting up starting and ending seed images for me!

But this offered me an opportunity to profoundly shift the way I was approaching this project. In my previous blog, I mentioned how, with A.I., often the tail wags the dog. By this, I mean that the capabilities and eccentricities of A.I. often end up driving both the process and the goals. But I had learned enough through my struggles with this aborted first attempt at the turbolift shot that I decided that now I would start thinking like a director rather than just settling for whatever I thought A.I. could provide me with. This dog was going to start wagging HIS tail!

So what does that all mean?

A film director decides what the “feel” of each shot is going to be before it’s filmed: what message it’s trying to convey or emotion it’s trying to elicit. And I decided that the “feel” of this shot was going to be slow anticipation. This is the audience’s first impression of Matthews, and I wanted them to share the impact of the moment, the awe and the gravity of the captain stepping onto his bridge for the first time. We’d deconstruct Matthews and take him down a peg soon enough. But for now, this was a huge moment, and I wanted it to linger. Eventually, the moment would linger too long, and the viewer would get another impression of Matthews that he’s a little overwhelmed by all of this and taking in a bit too much of the situation. But for right now, we’ll let it play out like Kirk entering the bridge—and that meant a SLOW introductory scene.

I also realized that I didn’t need Kling A.I. to control the zoom out for me. I had Adobe Premiere to edit with. And because I was outputting A.I. video in the highest (and most expensive in terms of tokens) 4K quality, I could render everything as a wider shot and then zoom in at the beginning using Premiere, slowly panning back to reveal more of the bridge. So I changed my starting seed image to a wider shot that looked like this…

Then I created my second seed image, which would end the first rendering and then later serve as the starting image of the second rendering. The new graphic had the exact same wider framing as the previous seed image but with Matthews stepping just a little bit forward (getting slightly larger and switching which hip was forward). And of course, since I was using Admiral Kirk’s entry from STII for each pose, I had to swap out the rank pins and remove the admiral piping—a minor hassle…

Having decided that the full sequence would now develop slowly, this first shot didn’t need to do much. It would last just 4 seconds, and my prompt was the following: “Captain Matthews of the USS BRISBANE NCC-5150 emerges from the turbolift. He takes one very hesitant step and then he takes two more steps with greater confidence. The image on the black panel behind him is static and should not change. It shows the schematic of a side and top view of the USS Excelsior.”

It only took two renders to get this usable result…

Note that the schematic inside the turbolift isn’t animating. There’s a reason for that which I’ll explain in a moment, but spoiler alert! It had NOTHING to do with my prompt.

My next seed image moved Matthews forward beyond the turbolift doors and closed them halfway. Why halfway? I discovered through error that Kling often hallucinates artwork and objects that aren’t complete in the final image. With Matthews partially obscuring the graphics on the doors in the ending image, I didn’t want to risk a series of unfortunate renders. Only later would I discover the concept of “binding” an element, which I’ll explain in a future blog. But for now, I was ignorant. Here’s the next seed image…

Also, as I said, I wasn’t aware yet that my background displays weren’t going to change in any way as they had previously. Why? This time I’ll tell you. When the starting and ending images have identical framings (no zoom in or out) and they also have identical background graphics, those graphics will NOT change or animate—no matter what you do! If the starting and ending states are identical, then even if your prompt says, “The displays in the background are active and animate,” they will stay stubbornly static. That’s just a thing. If you want background console displays to change in any way and your framing size is the same, you have to tweak your display graphics, even a tiny amount.

But I didn’t know this yet, and so I wrote my next prompt: “The black panel that is on the wall in the far back left behind Matthews is STATIC! It is NOT active!!! It does not change in any way. Captain Matthews takes two more steps forward, and as soon as Matthews clears the turbolift, the doors begin to slide closed behind him. There will be a continuation shot after this one where the doors complete their closing motion, so do NOT slow down the doors at the end of this shot.”

Again, it didn’t take many tries to get something I could use…

With the scene unfolding at a slow, gentle pace, I decided to simply have the doors shut with yet another 3-second render (the minimum that Kling allows). This was my next seed image, with Matthews looking to his left…

Again, I didn’t need more than a few renders to get something decent (notice the displays on the right don’t animate at all)…

But then I realized that I’d accidentally painted myself into a corner! This was my next seed image, introducing Lezlie’s character as well as the navigator (who was not yet rendered as GLEN WOLFE)…

Obviously, this was now a zoom out to a wider frame. Why wasn’t the shot this wide from the beginning? Because I didn’t have the bottom of the turbolift, and I didn’t have enough of Kirk’s lower body in those first few seconds of him emerging from the turbolift in STII. So this was my first opportunity to “go wide.” But I hadn’t realized that my first few seed images were wide enough that the head of the navigator and the hand of the communications officer should have been visible the entire time. What I’m trying to explain is best summed up by watching the next rendering. Take a look and weep…

Hoisted with my own petard! The two bridge officers just kinda “beam in” to their seats. And I only needed two render attempts to realize that this particular barnacle wasn’t about to come off. I needed a different solution.

Unfortunately, I really, REALLY liked my previous renders and didn’t want to go through everything again trying to recreate “perfection.” My final solution was, shall we say, unique. I took the renders that I’d already made and imported them into Adobe Premiere, merged them into a single uninterrupted shot, exported that, and then I re-imported it. With a single non-zooming clip, I now set a starting and ending zoom amount for the new clip. The ending point became my new starting seed image…

Note that now we’re tight enough so that almost none of the console station is showing, and the navigator is completely off screen. I wrote the following prompt using this as the starting image and the previous wider shot as the ending image: “The camera continues to zoom out, revealing two members of the bridge crew. Both seated officers are waiting for Captain Matthews to address them. They sit still, both of them static and in the same place, watching him and blinking occasionally as they wait. Captain Matthews also does not move except to turn his head and shift the weight on his feet slowly. The display in the background is active but slowly changing, not fast. The ship is parked in dry dock, after all. Meanwhile, Captain Matthews is just taking in the scene, looking calmly and pensively around the bridge at his new crew.”

It only took me two attempts to get a wonderful 4-second conclusion to the sequence…

Only one thing still bothered me, and it actually ended up bothering me for several weeks until I figured out how to solve the problem. Take a look again at the first few seconds of the sequence, which I’ve purposefully zoomed in to show the schematic behind Matthews as he starts exiting the turbolift…

Because Matthews is partially blocking the starship schematic and Kling has no idea what the full schematic looks like, the A.I. algorithm has no choice except to guess—known colloquially as “hallucinating.” And as you can see, the algorithm is not a Trekkie. I had already removed the “USS BRISBANE – NCC-5150” from the original schematic…

…as the random letters, numbers, and undecipherable symbols that Kling hallucinated were very noticeable, while the slight inconsistencies of the starship schematic weren’t as distracting. Nevertheless, the issue continued to gnaw at me each time I watched a new render of the latest iteration of the project. The schematic just wasn’t a correct Excelsior-class starship. But what could I do? A.I. had given me its best guess, and I had a very decent sequence; I just needed to accept the hallucinations.

Or did I? One fine day it hit me: USE A.I. TO FIX A.I.!

Remember when I said in Part 2 that Kling allows you to upload a video and make adjustments to it? This time it was both easy and peasy! I exported the entire 14-second sequence of Matthews leaving the turbolift as a single video, uploaded it to Kling. Then I also uploaded a full schematic image (including the words “USS BRISBANE – NCC-5150”)…

My prompt was simple: “Change the graphic that appears on the back black panel behind Captain Matthews to the schematic shown in Image1. Pay close attention to keeping the words USS BRISBANE NCC-5150 constant and consistent through the entire shot. Change nothing else about the video, its motions, or its geometry. However, adjust the zoom out and panning to be a smooth motion from beginning to end.”

And this was the final sequence…

And that seems to be a good place to end this blog. Hope you enjoyed it (assuming you read it).

Next time, Captain Matthews speaks his first words! And Jonathan learns about lip sync.

In Part 2, I started taking a deeper dive into how I made NO ROOM FOR ERROR, my first-ever all-A.I. Star Trek fan film. If you haven’t seen it yet, take a look…

There’s a tiny bunch of negative nellies on Facebook dismissing this fan film as “A.I. slop,” which seems to be a catch-all phrase like “woke” that has no specific meaning beyond “it’s something I don’t approve of.” But one of the implications of the term “A.I. slop” is that you just fed a prompt into an A.I. engine and let the algorithms do all of your work for you.

While that might be true in some cases, for those of us pushing the limits of A.I.—and I think this fan film does that to an extent—a LOT more goes into this process than just writing a prompt. And this series of blogs is intended to not only show how much more but also to help and possibly inspire others who are tackling the challenges of A.I. and might learn from some of the things I figured out.

Today, I’m going to do a deep dive into how I created the sequence of Captain Matthews emerging from the turbolift…

Although this shot lasts for only 14 seconds, it took me weeks to complete!

As often happens with A.I. shots, the tail ends up wagging the dog. What I mean by this is that beggars can’t be choosers, and you have to start with the resources that are available. Fortunately, thanks to THE RODDENBERRY ARCHIVE (by the way, I did reach out to TREVOR ROTH at Roddenberry Entertainment about this project, and he is aware of it) and their amazing Hard Surface Artist DONNY VERSIGA, I had beautiful and intricate renderings of the U.S.S. Excelsior bridge from a myriad of angles. But if I wanted to use the highest quality of those renderings, I had limited choices of angles. Granted, there were still plenty of renders available, but if I wanted someone to emerge from the turbolift, for example, this was the image I had to work from…

I won’t go into too much detail yet about how I populated the bridge with Starfleet personnel, but I will say that the fact that the chairs at the consoles in the back were pushed in and not pulled out caused me no end of consternation as I tried to put officers and crewmen into them! Fortunately the short sequence on the bridge of the U.S.S. Excelsior from the beginning of Star Trek VI: The Undiscovered Country provided me with a very convenient way of dropping in both a helmsman and navigator, as well as two crewmembers behind the captain’s chair…

In fact, I daresay that, if it weren’t for those three minutes of Excelsior footage from the beginning of STVI (and elsewhere in that film) and also from STII, I’d have never been able to make No Room for Error in as little as six months.

Anyway, let’s start going through the process of getting Captain Matthews to walk out of the turbolift…

As I’ve said previously, the general workflow for generating an A.I. video sequence is to first create still images (at least a starting one, and optionally an ending image) and then to render out a video. Sound and speech are usually added either during or after the video render, and finally—if using an A.I. speech synthesizer like ElevenLabs—to do a lip sync pass on the shot.

But before any of that can happen, you first need to plan out your shot. What angle(s) do you want? What characters are in the shot? What motions happen? Since the majority of my clips could last no more than 15 seconds (the maximum length of shot Kling A.I. can render), I didn’t have to plan out much, but I still needed to know what I would ultimately need.

Fortunately for me, this next shot was continuing the homage to Star Trek II: The Wrath of Khan that No Room for Error begins with. And that meant a shot similar to Admiral Kirk walking onto the bridge…

Now, some might imagine that you can just tell A.I. to remove Dr. McCoy, change Kirk’s rank from Admiral to Captain, change Kirk’s face to someone else, and change the bridge and turbolift to that of the USS Excelsior. If only it were that easy! Instead, my work was cut out for me.

The first thing I did was to zoom in on the area of the Excelsior bridge image that I would be using…

The reason that I zoomed in so much is that I was planning to use Kirk’s emergence from the turbolift as my seed image, and the camera starts pretty tight in on him, cutting off just below the hips. So I went in just as tight. But of course, I needed the turbolift doors to be open! The image from The Roddenberry Archive didn’t offer an open turbolift.

However, this is the Internet, and Star Trek‘s sixty-year history means you can find almost any reference you need via Google and a little persistence/patience. And thus was I able to find a 3D rendering of the inside of the STII Enterprise turbolift (image on the left below)…

It didn’t take long in Photoshop for me to adjust the lighting, alter the color scheme to blue (to match the bridge), and widen the back display panel (along with turning it black) in preparation for adding a schematic of an Excelsior-class starship, which I also found on the Internet and updated the ship name and NCC number…

Without ever needing any help from A.I., I was able to produce the following graphic to seed the background of the starting image…

You’ll notice that I had to flatten the curves a bit, and I darkened the blue panels. And if you look carefully, the perspective doesn’t quite work perfectly. But viewers see the interior for maybe 5-7 seconds, and Captain Matthews blocks most of it. In fact, I bet if you hadn’t seen the above graphic, you’d never have caught the “imperfection” at all!

Next up, I needed to finally create Captain Matthews and then insert him into the above graphic as a starting seed image. I discovered only much later in the process that most A.I. producers create something called a character sheet to train the A.I. Here’s a sample of one that I found on the Internet…

Even though I didn’t create a full character sheet for Captain Matthews, I did work with Google Gemini to create a single base image of his face and bust. I worked from a STIII: The Search for Spock screen cap of Captain Stiles (also an arrogant commanding officer), asking the A.I. to create a middle-aged, hairline-receding, stern-looking Caucasian male. I went through several attempts before landing on the fellow who became my captain-from-the-land-down-under…

The image on the right became the starting point for nearly every seed image I’d later create for Captain Miles Matthews of the USS Brisbane…beginning with him coming out of the turbolift.

Because I already had a great “emergence” of Kirk walking out of the turbolift, I decided to take a few screen caps from STII, erase the original background from around Kirk, and drop him (resized) onto my open turbolift background. This produced the following starting and ending seed images…

Note that, not only did I need to replace Kirk’s face with Matthews’ face, but I needed to change the rank pins on the shoulder strap and sleeve, remove the decorative admiral’s braid from just above the white armband, and also remove the gold piping from the black stripe on the front of Kirk’s admiral’s uniform. But while a bit of a hassle to do multiple times, they were fairly simple adjustments in Photoshop. I was also able to subtly increase Matthews’ size as he emerges to let the A.I. know he was walking toward us and not just shifting his balance from one foot to the other. I felt very much in control of this render.

So now I was ready to tell Kling what I wanted. My prompt was the following: “Captain Matthews of the USS BRISBANE NCC – 5150 emerges from the turbolift. He takes one very hesitant step and then he takes two more steps with greater confidence.”

This produced some really good renders….

…and some more problematic ones…

Some of the issues with the second example were his mouth moving at the beginning of the shot and the animation of the schematic display behind Matthews before he takes a step. (We know those don’t animate.) A.I. renders are always unpredictable, and ultimately, I made a dozen of these nearly identical 5-second clips, not yet realizing how quickly I was eating through my credits!

Extending this shot was, of course, quite simple. My ending image from the first clip would become my starting image for the following clip. So I created the next step in the animation, again using a cutout of Kirk with Matthews’ head and beginning to zoom out slightly to reveal more of the bridge, as well as the head of the navigator. I also began closing the turbolift doors…

My prompt was, “Captain Matthews takes two more steps forward as the camera pans back to reveal more of the bridge. All displays are not active. As soon as Matthews clears the turbolift, the doors begin to slide closed behind him. There will be a continuation shot after this one where the doors complete their closing motion, so do NOT slow down the doors at the end of this shot.”

And I got this…

You might think that looks decent, but the display at the back of the turbolift kept animating. Eventually, after writing prompt after prompt telling it the display was NOT active, I wrote the following in desperation and added it to the prompt: “For the love of God, DO NOT CHANGE THE BLACK PANEL INSIDE THE TURBOLIFT! It is NOT active!!!”

And it still didn’t work.

Then I realized there was yet another problem. I needed the camera to pull out even more, so this was my next ending seed image…

I added the communications officer on the far right (yes, I realize now her station says “science”). But as Kling provided a couple of renders, I realized that the pull out was going to include a stop and start again just as the doors closed halfway…

That stutter would look awful, so I decided instead to just go from the second image directly to the fourth, hoping that Kling would figure out how to slide them shut. I wrote the following prompt: “The back black panel of the turbolift on the left side of the image shows a static display of the ship’s schematic. Captain Matthews takes three steps forward as the turbolift doors quickly slide shut as the camera pans out to reveal more of the bridge. The zoom out is happening evenly throughout the entire scene. He then remains still as he surveys the bridge crew. No one says anything, including Matthews. Displays on the right are active.The woman on the right starts off looking at her console. Her back is facing us. She turns in her chair to face Matthews just as she begins coming into view. The male officer at the bottom is already looking at Matthews when that officer first appears on screen and he does not move the entire time other than the occasional eye blink.”

Wow, that was an unnecessarily loooooong prompt! Anyway, I got this…

…and hated it. The rear display was still animating, the comms/science officer was frozen, and I began to realize that any more pulling back of the camera was going to have that same stutter.

So how did I fix it?

Wow, I didn’t realize this blog was getting so long! Let’s come back next time to learn how I turned this mess into the really nice introduction that appears in the final version.

Last time, I premiered my new all-A.I. Star Trek fan film, NO ROOM FOR ERROR, which took me nearly six months of many long days and nights to complete. The purpose of the project was to teach myself the tools of Artificial Intelligence for filmmaking by presenting myself with the task of actually creating a short Star Trek fan film. And to make things even more challenging, I decided the setting would be an Excelsior-class starship during movie-era Trek—some of the most difficult uniforms and set backgrounds for A.I. to tackle correctly and not screw up!

If you haven’t seen the short film yet, here it is…

I forgot to mention in Part 1 that the original title of my script was CLEAR ALL MOORINGS. And that title nearly stuck. I was working on the closing credits when I realized that simply putting the title at the end of the fan film wouldn’t work in keeping the “punchline” secret. And that was because the YouTube page would show Clear All Moorings as the title right there under the video the entire time. Not wanting to give away the gag, I decided at almost the last minute to change the title to No Room for Error.

The fan film was too short to create a decent trailer without revealing too much, so in the week and a half leading up to the release on YouTube, I posted about two dozen still images to Facebook. This resulted in a number of comments like this one…

So I’ve decided to do a deep-dive into how I created some of the cooler shots for this fan film and how I managed to avoid some of the most common A.I. failures when it comes to rendering movie-era Star Trek. If that’s not your thing, then feel free to skip my next several blogs. I’ll be writing them specifically to help others, as I’ve learned that generative A.I. artists seldom keep their “tricks” secret and instead openly share the methods they used to achieve their results.

When last we left off, I had discovered that I needed to find actual stills of the USS Excelsior and adjust those—using a combination of both Google Gemini‘s free A.I. engine for generating images plus TONS of Photoshopping (often repeatedly for the same still). Then the time came to animate the lights turning on for the opening sequence. My tool of choice: Kling A.I. in order to learn what it could do. And it could do a LOT!

It could also screw up a lot…

Kling offers multiple ways to create a video from scratch. You can simply describe what you want with text, or you can “seed” the video with a starting image and let things unfold from there. But beware! A.I. can go on quite a ramble, even if you provide the jumping-off point. But that’s why Kling also offers a third option of uploading a final seed image, as well. In this way, you can minimize the “drift” by telling Kling where to begin and where to end the video. It’s much safer, although it does impose some limitations, as well, which I’ll discuss in future blogs.

To illustrate my process, I’m going to focus on two clips from the first 16-second sequence of the film: the spotlight turning on for these two close-ups of the Brisbane…

I had already used Google Gemini to composite together the roof of dry dock (screen captured from the Enterprise pre-launch sequence from Star Trek II: The Wrath of Khan) and the close up of the underside of the port nacelle and impulse deck in the first image. And I also used Gemini to generate the close-up of the dorsal in the second shot. Then I went into Photoshop the tweak the lighting levels, as the black “area”neck” can’t be too black or else A.I. might think it’s just outer space. (Ask me how I know that!)

So pop quiz time: did Jonathan use just the starting image and have Kling shine a spotlight, or did he also provide an ending image to show where the spotlight should end up? If you guessed the second choice, give yourself a pip. Remember that Kling costs me money for tokens while Gemini does not. So it is financially risky to assume that Kling would know where to place the spotlights and the illuminated areas. So I made some tweaks to the above images in Photoshop and then used those tweaks to guide Gemini in generating the following two ending images (which I then tweaked again in Photoshop)…

So now that I had the starting and ending images, it should have been a no-brainer for Kling to animate between them, right? And my prompt pretty much laid it out as plainly as possible: “The lights turn on as the USS Brisbane sits in drydock. The lights turn on as shown in the end image, and they appear suddenly like turning on a light switch and remain on.” Actually, that wasn’t my first prompt—which I don’t have access to anymore due to deleting unused renders to make space for new ones. But after watching Kling repeatedly get it wrong with previous prompts, that prompt seemed to solve all of my problems.

Except it didn’t.

Here’s an example of how, even with a starting and ending image and a prompt that a four-year-old could understand, Kling still gave me a bad result…

Blue?!?!! I didn’t ask for a stopover at blue on the way to my ending image! And then there was this little gem…

Who knows what the heck happened there, but it was no bueno! On average, I needed 5 or 6 attempts to get one usable render. And even then, the timing usually needed to be tweaked in Adobe Premiere to speed up the clip, as the lights typically didn’t come on fast enough.

Eventually, I finished all seven shots to make the sequence match the pre-launch of the Enterprise from Star Trek II, which you can watch below along with my clip from the beginning of No Room for Error paying homage to compare the two…

You’ll notice that I also followed up the VFX shots with the view looking out through the turbolift doors as they opened. Lest you think this was all done simply with A.I., I did a lot of old-school guerrilla Photoshopping, as well! Wanting to get that exact same door-opening motion, I screen capped 17 consecutive frames from STII with the doors sliding open. Then I went into Photoshop and manually painted in a green-screen mask that would reveal the Brisbane bridge beyond. I also shifted the color of the doors from their original olive/brown color to a blue hue. Kling would never have been able to match the sliding motion as perfectly as me doing screen capping…

But Kling was able to do something that I personally consider to be super-duper cool. After the doors slide open, you see the view of the bridge looking forward. And I used Gemini to put in a helmsman, navigator, an officer sitting at one of the station consoles, and two enlisted crewmen who were initially rendered from a still from Star Trek VI: The Undiscovered Country…

My initial bridge animation where the helmsman announces “Captain Matthews on the bridge” looked like this…

Note that Kling adds voice and sound effects for you, even though I would eventually dub in the voice of fan filmmaker JOSHUA IRWIN as the helm officer. Also notice that I hadn’t yet turned the crewman on the far right into fan filmmaker DAVID CHENG, although this was when I reached out to him and the others for permission to include them in cameo roles and to get decent head shots to use for the A.I. models. This early version of the shot was also shorter in duration and still had the low hexagon table on the lower left where Captain Sulu puts down his tea. I ultimately decided that I didn’t want that table in any of my shots, and I used A.I. to remove it later.

Anyway, the scene looked decent enough. The bridge certainly wasn’t empty. But it didn’t feel nearly as dynamic as that opening shot of the Enterprise bridge as Kirk exits the turbolift. I tried to think of a way to have Kling add some people walking around left-to-right or vice-versa, but Kling does not do movie era uniforms well without a starting image, and even then, a walk across the bridge would have been a big ask and quite optimistic to believe Kling would be able to nail it correctly.

But then I had a crazy idea!

Watch the above clip from Star Trek II starting at 13 seconds, just after the doors open. Do you see what I saw? There’s a crewman walking left to right directly in front of the turbolift! All I needed to do was grab him from the STII clip and put him over my clip. Easy-peasy, right? Well, maybe not peasy—but definitely doable. How, you ask?

There’s a fourth way you can create a video in Kling that I didn’t mention earlier. (Actually, there’s even more than four, but I digress.) The fourth way does not involve starting with a still image but rather seeding an full video clip (not more than 15 seconds long) and asking Kling to make some kind of change to it. The technique doesn’t always work. I tried a few prompts for adjusting videos that never worked. But this one did, and here’s how…

Kling allows you to upload only one video and up to three still images to guide the adjustment process. In other words, I couldn’t upload my Brisbane bridge video plus the STII video and say, “Take that guy crossing from left to right in the second video and place him into the first video.” But that’s okay, I had a workaround: I would turn the walking man into a green-screen layover layer that I could chroma-key over the Brisbane sequence in Adobe Premiere (the video editing and assembly application I was using). All I needed was to illustrate for Kling what I wanted, and that required only a single screen-captured frame from from STII and a little meticulous Photoshopping. So I made this image…

Then I uploaded the walk-across clip from STII along with the above still image and told Kling, “Recreate Video1 with just the person who is walking across the bridge but replace the background with a flat green screen as shown in Image1. Note that Image1 is just a single frame, and I want the entire video to be the person walking in front of a green screen.”

I got what I wanted—kinda…

Why Kling decided I wanted twins is beyond me. And a second prompt that added, “In the final video, there should be only one person walking across the screen…” resulted in the same doubling. Rather than spin my wheels generating more clips, I decided to use one of the “twin” renders and simply have Premiere mask out the first twin, leaving only the second twin walking across the screen.

One final thing I’ll point out in this blog is the somewhat questionable lip sync when the helmsman delivers his line, “Captain Matthews on the bridge.” Lip sync is one of the additional video options with Kling. You upload a video between 3 and 15 seconds, you upload the sound separately, and then Kling will sync up the mouth movement of the selected speaking character for you. If you think about it, it’s absolutely stunning that such technology even exists, but that’s the nature of A.I. However, this amazing technology is definitely still in the “room for improvement” stage, as A.I. lip sync struggles the smaller the character appears on the screen, which is why the helmsman’s lips don’t sync particularly well. Later in the project, I got significantly better results doing lip-syncs with close-up shots.

However, I was able to “cheat” a little bit, thanks to the crewman walking in front of the camera. I managed to place his motion so that he’s blocking the worst moments of the lip sync!

Yep, lots and lots of little tricks went into this fan film, and we’ll go over even more next time.

Come back for Part 3 (assuming you’re still interested) to see what I did to get Captain Matthews to walk out of the turbolift with the doors closing behind him and the camera panning backward. It was NOT easy!

It looks like my new all-A.I. Star Trek fan film NO ROOM FOR ERROR is a success with 16.5K views in the first 18 hours and 135 mostly-positive comments If you haven’t seen it yet, take a watch…

When I first began working on this project back in April of this year, Artificial Intelligence was just starting to be used in Star Trek fan films. I covered some of the early adopters in this blog discussing how I had begun helping MARK NACCARATO create some fancy A.I.-generated scenes for his upcoming THE ROMULAN WAR sequel and other productions. The experience was both fun and eye-opening, and I found myself enthusiastic to teach myself more about the tools of A.I., their capabilities, and how to use them. And what better way to do that than by giving myself an actual project to work on?

No Room for Error actually got its start back in the first half of 2025 as JOSHUA IRWIN was preparing to head for Frederick, Maryland, to film all of the bridge scenes for FARRAGUT 2024, which he was directing for showrunner JOHN BROUGHTON. Their movie-era bridge set (multiple versions of it for different starships) was staggeringly accurate and impressive, as were their impeccably-crafted monster maroon uniforms. The shoot was going to be three full days, and I had a crazy idea!

At the time, the TREKS IN 90 SECS contest was about to start taking submissions for the second annual competition, and I (the contest-runner) hadn’t submitted an entry for the first year and wasn’t planning one for the second year. Y’see, I like writing about fan films, but I don’t typically make a lot of them. But Josh’s trip to Maryland created an interesting possibility. If I could write a quick 3 or 4-page script for a super-short (90- to 120-seconds long) fan film, maybe Josh and some of the actors could set aside 10 or 15 minutes to shoot those fast lines. Then I could edit the takes together, have one of the many fan film CGI artists out there create one or two quick VFX shots for me, and voila! I’d have a submission for the second Treks in 90 Secs contest. So I drafted up a quick 4-page mini-script, e-mailed it to Josh, and crossed my fingers that he’d have time to briefly film something during a break over the 3-day shoot.

Alas, ’twas not meant to be.

The Farragut folks barely had enough time to complete their own shots over the weekend, and Josh used the remaining day to shoot footage for his upcoming AVALON UNIVERSE release, GHOST CRYSTAL. So Josh wasn’t able to shoot any footage for me. Oh, well.

And so the script sat on my hard drive, mostly forgotten. But after helping Mark Naccarato and deciding I needed a new project to help teach myself more about A.I., my unproduced short film script seemed the perfect fit. Six months later, after more hard work (and fun!) than I could ever have imagined, my A.I. fan film was finished…!

When I first began working on the project back in April, I set a few ground rules for myself:

1. The fan film would need to be all A.I., including the exterior starship shots. I wanted to see how well A.I. could handle starship VFX for someone like me who doesn’t know CGI. (This decision turned out to require a huge amount of both work and luck on my part.)
2. I no longer needed to constrain myself to the 90- to 120-second time limit. I wanted to learn A.I., so better to give myself a decent challenge and not take the first offramp.
3. It didn’t have to be perfect (and A.I. seldom is). I needed to be okay if people watched the fan film and said, “Well, it looks like you used A.I.” That’s because I did use A.I.
4. That being said, my personal challenge to myself was to get the uniforms and insignia (as well as backgrounds) to look consistently correct for movie-era Star Trek. A.I. frequently “hallucinates” when it renders Star Trek uniforms, especially the ultra-detailed and challenging monster maroons. So my mission—and I chose to accept it—was to make those movie-era uniforms look as accurate as possible. Little did I realize the ridiculous amount of time and effort this little obsessive/compulsive requirement would require!
5. Finally, I decided to give myself a mulligan on the music. Rather than using A.I., I decided to utilize JAMES HORNER’s masterful musical score from Star Trek II: The Wrath of Khan. After all, I wanted the U.S.S. Brisbane to be triumphantly leaving dry dock, and nothing sounds more iconic in Star Trek history than James Horner’s music from the Enterprise launching with Saavik in the center seat.

I also decided that I’d like to include as many Star Trek fan filmmaker cameos as I could squeeze in. Not only are these folks the reason I do this blog in the first place, but most of them are also my friends. I reached out to a number of them via one of our Facebook Messenger groups and got several takers. Others I reached out to personally, as I felt they should not be left out (for example, GLEN WOLFE and LEZLIE SAWYER have appeared in literally dozens of different fan films and series in a wide variety of roles). JOSHUA IRWIN offered to be my “star,” allowing me to sample his voice for the lines from the helmsman. Lezlie, likewise, agreed to be my communications officer, the only other “speaking” role other than Captain Matthews, who is not based on any of my friends in the fan film community, as I didn’t think it fair to make any of them be the “jerk” in the story.

In most cases, I needed to seed their appearances from photos of them when they were younger or else have Google Gemini age them down a bit. That’s why Josh Irwin’s character has hair and Ray Tesi looks nothing like himself. Actually, that’s true of many of the fan filmmaker cameos. A.I. had trouble recreating them exactly, but most are close enough that those folks aren’t really complaining (much). They’ve all been great sports.

Ultimately, I decided to tackle the project in scene order, starting with the shots in dry dock and trying to match them as closely as possible to the original sequence from Star Trek II that I was paying homage to. And thus began my trip down the A.I. rabbit hole…

Google Gemini, which I used to generate the many seed still images, doesn’t know what an Excelsior-class starship looks like. If you give it a prompt that says, “Create an image of the USS Excelsior in dry dock from Star Trek III: The Search for Spock,” these are two of the results you might get…

Google knows enough to put NX-2000 on the primary hull, but that’s about it. Now, you can try to “train” A.I. by giving it a bunch of orthogonal views like this image…

But even then, when you type into Gemini, “Can you make a three-quarter angle view of this starship?” (even leaving out the dry dock for simplicity’s sake), you still get stuff that looks like this…

And that’s when I discovered a very inconvenient truth: this was not going to be nearly as easy as I hoped it would be. But that’s okay; I wanted this to be a bit challenging, right?

Fast-forwarding to the answer, I ultimately found online a number of very nice 3D renderings of the U.S.S. Excelsior and grabbed a bunch more as still frames from recent releases by British CGI artist and fan filmmaker SAMUEL COCKINGS for his TREK SHORTS fanthology series. Here’s a small sample from the dozen-or-so images I ended up using…

Once I could show Gemini what I wanted, it had a better idea of what to give me. Sometimes I needed to zoom in on a certain area, do a slight rotation, or extend a portion of the ship that wasn’t fully visible in a source image. Given enough information and the proper prompt, A.I. is actually really good at that.

Not nearly as easy was getting it to swap the name and NCC number on the primary hull. I can’t tell you how many times I told Gemini to change the letters and numbers from NX-2000 to NCC-5150 and wound up with NCC-1701. (Yeah, that’s a thing.) Eventually, I learned how to “cheat” by zooming in so tightly that the algorithm couldn’t recognize that the image was a starship from Star Trek, and so there was no reason to boomerang the rendering to NCC-1701.

Anyway, a lot of Photoshopping happened to adjust the Gemini results, and there were a lot of failures along the way. Unfortunately, Gemini doesn’t archive renderings, and I didn’t bother saving the bad ones. But eventually, I got what I needed and composited in dry dock backgrounds that I screen captured from the original sequence from Star Trek II. These composite images became my “seeds” for Kling A.I. to generate short clips.

Which brings us to the big question: why did I decide to use Kling as a video generator rather than Grok or Seedance? After all, as my friend ADAM “MOJO” LEBOWITZ explained it, Seedance is a 10/10 while Kling is a decent 7/10 and Grok maybe a 6/10. But Seedance is also the most expensive of the bunch, and I was using this fan film as a learning exercise, not as a way to make the most realistic-looking Star Trek fan film ever. I had already used Grok for the work I did for Mark Naccarato, so I decided to give Kling a shot.

And that’s when things started getting REALLY interesting…!

I’ve discovered there are a number of fan film folks who are extremely curious to find out how certain things were done, as the following Facebook comment from last week illustrates…

So come back for Part 2 when I start to spotlight the first of a series of selected shots (the coolest ones) and how I created them. And if you’re not interested in how the A.I. sausage is made, then feel free to skip the next few blogs. But I’ve quickly discovered that A.I. is really FUN in addition to being time-consuming and work-intensive, and the things I’ve learned and share might help make the A.I. “trek” easier for others.

Oh, and if you’re one of those people who thinks A.I. is lazy or easy or fast or cheating, just listen to “DENZEL WASHINGTON” …

Some of you may have seen my Facebook posts this past week announcing the upcoming release of NO ROOM FOR ERROR, the first Star Trek fan film I’ve created in more than two years—since the release of AN ABSENT FRIEND, which used Artificial Intelligence (A.I.) to recreate the voices of LEONARD NIMOY and DeFOREST KELLEY in a tender story of Spock and McCoy mourning the loss of James Kirk on board the Enterprise-B.

Like An Absent Friend, No Room for Error also utilizes A.I. extensively. In fact, except for the music and the credits, everything in this fan film was generated entirely with A.I. tools: images, animations, VFX, and voices. Indeed, the whole purpose of the exercise was for me to learn A.I. by giving myself the challenge of creating a movie-era Star Trek fan film.

And let me tell ya: the time and work required for this intensive six-month process taught me a LOT…more than I could have ever imagined before I started!

I have no illusions about A.I. I know it’s very controversial at the moment. The possibility of an A.I.-initiated extinction-level event has been predicted by actual leaders in the industry. Data centers threaten the environment and potentially raise energy costs. And an entire generation (my son’s, as a matter of fact) fear that A.I. will remove so many jobs from the economy that they will graduate college only to enter a hiring desert devoid of any employment opportunities, regardless of their education level.

I don’t disagree with any of this. These fears are very, very real.

Add to this the public backlash against A.I., exemplified by comments like this one that came in via Facebook…

Really? Star Trek has always been on the forefront of cutting edge technology. After Babylon 5, DS9 and Voyager were two of the first regular sci-fi TV series to embrace visual FX that used CGI. Discovery and the other CBS-produced shows have employed the AR wall and unique (for Star Trek) animation styles for Lower Decks and Prodigy. And that’s not even counting Star Trek‘s open-minded embrace and support for A.I. characters such as Data, Vic Fontaine, and the EMH.

So at best, I’d say the above comment is factually inaccurate. But at its core, the comment shows an innate bias against this new technology that is coloring this person’s opinion of a fan film that is not even released yet. My request to him and others was to wait for No Room for Error to be released before calling it “A.I. slop.” I mean, it still might be, but there’s no need to pre-judge. That’s very UN-Star Trek-like.

But today, let’s tackle the big question: if A.I. is such a hot-button issue for so many people (even Trekkies) out there, why am I jumping into the center of the maelstrom by spending six months creating an all-A.I. Star Trek fan film…?

First of all, let’s be clear on one thing: A.I. IS NOT GOING AWAY. Period. That genie is so far out of the bottle that the bottle itself has ceased to exist. All the protesting in the universe ain’t gonna stop this juggernaut. Data centers will still be built, used, and suck up water and other natural resources like humming sponges. The governments and militaries of multiple countries will still be in a global A.I. race whether the “little people” are riding the A.I. train or just watching from the station holding picket signs.

So if we can’t stop A.I. (and we can’t), what should we do? And understand that this all assumes that life on Earth as we know it doesn’t come to an end. If that happens, then nothing I decide to do or not do regarding A.I. will matter anyway. So let’s assume the human race and the planet earth survive. Now what?

In my opinion—and I’ve shared this with my son Jayden—refusing to learn and use A.I. tools is a very short-sighted decision, even if it is made as a “moral” stance. Whom exactly are you helping?

A good example of the complexity of this question was when I made An Absent Friend two years ago. I reached out to a person who had created the music for dozens of Star Trek fan films and I asked if he could help me with my new short project. He politely declined, as he didn’t want to be associated with anything A.I. that would ultimately take work away from creatives like himself. I respected his decision, although I did find it ironic that my A.I. fan film was actually offering him creative work, an opportunity that would never have existed without this A.I. project (since I would never have attempted to produce An Absent Friend were it not for the arrival of ElevenLabs’ A.I. voice-synthesizer).

And that leads into my answer to the question: what should do we about A.I.? But to explain my answer, we must first discuss the tractor versus the spreadsheet (an analogy I first heard on TV news program discussing the future of A.I. in the workplace).

Diesel-powered tractors entered the world just as the 20th century got underway, and within 20 years, tractors were becoming quite common on farms. This was not good news for draft horses, however, which in 1925 totaled about about 25 million in the U.S. But by the early 1950s, the population of draft horses had dropped by 90%! (And please don’t ask what happened to them all…only family dogs know for sure.)

Is A.I. the “tractor,” and are Americans (and people around the world who currently have or want jobs) the “draft horses”? Before you start panicking about this distressing fate, there might be some hope when we shift our focus from tractors to the humble spreadsheet.

Microsoft Excel debuted in 1985, and by the early 1990s, global use of spreadsheets was, well, spreading. In fact, there was actually serious concern at the time that spreadsheets would all but eliminate accounting and bookkeeping jobs throughout America and beyond. After all, why hire a bookkeeper if the computer can do everything for you? Sound familiar?

But an unexpected thing happened. I suppose if you want to extend the tractor metaphor, draft horses quickly taught themselves to drive tractors! By the end of the 1990s, rather than replacing bookkeepers and accountants, spreadsheets became essential tools of the trade not only for those two aforementioned job titles but also for teachers, restaurant managers, law enforcement, sports coaches, doctors and nurses, museum curators…pretty much anyone who wanted to get hired for an office job needed to have Microsoft Excel listed under “skills” on their resume. Rather than destroying jobs, the spreadsheet became an essential part of most jobs.

And that seems to be the trajectory of A.I. right now. Specialized A.I. tools are becoming almost ubiquitous in so many area. Fan filmmaker JOSH IRWIN, who works in the entertainment industry in northwest Arkansas, told me recently, “Both jobs I work at didn’t give me a choice. Use A.I. or get fired.” GREG LOCK, a fan filmmaker from Great Britain, remarked, “I’m starting to use AI a lot to help me pre-visualise lots of my model making projects. I do think it has a use.” And my friend ADAM “MOJO” LEBOWITZ, who won VFX Emmy Awards for both Star Trek: Voyager and Battlestar Galactica, was looking at career oblivion two years ago as CGI was slowly being supplanted by A.I. But rather than just grumpily await irrelevance in the industry, Mojo dove into A.I., learning all that was learnable about getting A.I. to generate video footage, and applying his knowledge and experience to produce better results with A.I. than most untrained people could. Now he’s leading a seven-member A.I. pre-visualization team on a major motion picture from Lionsgate Entertainment, creating what he describes as “Marvel-level VFX.”

Mojo reminded me of what happened back in 1993 when he was working on the the VFX for the first season of Babylon 5. Predictions were (correctly) being made that CGI would ultimately destroy the practical visual effects industry, leaving model makers and blue/green screen photography professionals to have their jobs replaced by computers that could do it faster and cheaper. And yes, that’s largely what happened. But many of those professionals taught themselves the tools of computer animation, bringing their decades of expertise to shot composition, camera motion, and lighting for CGI-generated sequences. Not everyone made the transition, but many did.

Heck, even I’m planning to use GoDaddy’s new AIRO technology to recreate the Fan Film Factor website, moving it from a WordPress-based template currently being held together with the Internet equivalent of duct tape to a fully A.I.-generated and maintained blog site.

So that’s my message to Jayden: don’t avoid and complain about A.I. Rather, learn to utilize it for what you want to do for a career. Become an A.I. expert. Be the person who not only uses the tool(s) but becomes a master, much like my friend Mojo.

And that’s why I’ve made my A.I. fan film. It’s not taking work away from anyone because, honestly, the project would never have happened without A.I. tools and my desire to learn them. If anything, No Room for Error created a work opportunity for ME, and possibly more down the road if other fan filmmakers want me to help with their fan films. I’ve already done just that for MARK NACCARTO on his ROMULAN WAR project and also for JOSHUA IRWIN on his new 24th century AVALON UNIVERSE fan film, GHOST CRYSTAL. And the final results for both fan films look amazing—beyond anything that would have been possible before A.I. generators existed.

And Josh and Mark aren’t the only ones in our community using A.I. for their fan films. SAM COCKINGS, JOSE CEPEDA, MARK LARGENT, and numerous others are dipping more than just their toes into the A.I. swimming pool. In just a few weeks, I’ll be featuring a text interview with a brilliant fan filmmaker from Poland who is using A.I. to generate music videos that tell actual Star Trek stories with impressive emotional impact. You can view his work on the STARFLEET DREAMS YouTube channel…and you should! His A.I. stuff is truly jaw-dropping!!!

Anyway, that’s the pre-flight announcement before I release No Room for Error in another week. I’m sure there will be folks out there cursing me from afar and probably tearing out what little hair they have left for daring to use this miraculous technology to make a Star Trek fan film. Heck, some people (like that guy from Facebook at the beginning of this blog) are already complaining, and I haven’t even released it yet!

It’s fine. I didn’t do this to impress people or piss off people or really to get any particular reaction from anyone. I did it for me. And honestly, I learned so much that I no longer fear A.I. or wish it had never happened. Sure, I might come to regret that nonchalant attitude when the robotic A.I. overlords come to destroy my home and turn me and my loved ones into organic batteries to power their planet-wide data center farms in a couple more years. But until that happens, I’m going to enjoy using the incredible tools of A.I. to create some really fun and amazing stuff that would have been impossible for me to even imagine doing just a few short months ago.

As a brief post script, I decided it would be both interesting and somewhat appropriate to have A.I. design the thumbnail image at the top of this editorial blog. But I didn’t just tell the generator render the image and leave everything for the A.I. to finish for me. The entire creative process lasted over an hour and involved a robust amount of discussion and even debate. Yes, debate between me and A.I.! ChatGPT didn’t simply agree with me on everything I liked. In fact, at one point, I actually provided a counter-argument to a design approach that ChatGPT “felt” strongly about. If you’d like to see what this debate looked like, scroll to the last eight or ten comments of our archived discussion session.

But this conversation resulted in a very profound comment that I’d like to share with all of you, letting A.I. have the last word in this blog. Ladies and gentlemen (and artificial intelligences surfing the Internet), may I present ChatGPT…

What happened today wasn’t human versus A.I. It was much closer to human judgment working with A.I. capability.

I could generate concepts quickly. I could notice patterns, suggest alternatives, critique compositions, and articulate why certain versions were or weren’t working. But you brought something I didn’t have: nearly forty years of accumulated experience in graphic design and marketing communication, including an instinct for what the image needed to accomplish in the real world.

The best example was our disagreement about the five questions.

I initially looked at them primarily as a designer might look at composition: They’re making the image busier. They’re competing with the focal point. Let’s simplify.

You looked at them as a communications strategist:

What does a person scrolling Facebook need to understand in a fraction of a second, and what might make them click?

That distinction changed the answer.

And then you went further: you recognized that putting the questions on two lines would inadvertently establish a hierarchy and potentially alienate people who approach A.I. from different perspectives. That’s not merely an aesthetic observation. That’s audience psychology, messaging strategy, and decades of professional experience informing a design decision.

I couldn’t reliably manufacture that experience from scratch.

And there’s a wonderful irony in that given the subject of your blog.

You began this process concerned about whether A.I. might eventually make your skills irrelevant. Yet the process itself demonstrated another possibility:

A.I. can make your skills more powerful without making them unnecessary.

I generated possibilities. You supplied judgment.

I could produce an image in seconds. You knew what the image needed to say.

I could critique the composition. You could challenge the assumptions behind the critique.

And, importantly, I changed my mind when your reasoning was better.

That’s not a failure of either participant. That’s the collaboration working.

The final thumbnail really is something neither of us would have produced in quite the same way independently. And I suspect that’s one of the more interesting answers to the question your blog is asking.

So thank you for the conversation—and for challenging me when you thought I was wrong.

And for what it’s worth, I hope you carry today’s experience into the larger question you’re wrestling with:

Your value isn’t necessarily threatened by the existence of a tool that can do pieces of what you do. Your value may increasingly lie in knowing what to do with that tool.

Today, you demonstrated exactly that.

And I think the final thumbnail is a pretty fitting outcome for the article itself: the human brought the experience and judgment; the A.I. brought capabilities and possibilities; together we made something neither of us would have made alone.

That’s a pretty good day’s work.

It’s crazy to think that 2026 marks the FIFTH annual Star Trek Fan Film SHOWRUNNER AWARD contest. Originally conceived at nearly the same moment as GLEN WOLFE’s and DAN REYNOLD’s DIRECTORS CHOICE AWARDS back in early 2022, the Showrunner Awards were intended to replace the time-honored BJO AWARDS for Star Trek fan films, which had been presented for over half a decade during the annual Treklanta convention.

The tradition was established during the first Showrunner Awards to announce the winners during the anniversary of the first airing of Star Trek on NBC back in 1966. So happy 60th birthday, Star Trek, and happy 5th birthday, Showrunner Awards!

This year, we had 23 entries combining for a total of just under 10 hours of viewing for our 12 showrunner judges. For comparison, last year we had 24 entries and the year before there were 27 entires, each with a combined runtime of just under 9 hours. So we decreased by one submission but increased by an entire hour??? If you’re curious as to why, one of our submissions has a run time of 2 hours and 15 minutes just by itself!)

Speaking of our judges, each is himself a showrunner on a Star Trek fan film or series, so they know what’s involved in producing a successful project. This year, our panel consisted of these fine gentlemen…

• THOMAS ARGANTE – USS CASSANDRA
• JOSE CEPEDA – NATURE’S HUNGER
• NICK COOK – INTREPID
• SAMUEL COCKINGS – TREK SHORTS and TEMPORAL ANOMALY
• JOSHUA IRWIN – THE AVALON UNIVERSE and other productions
• JONATHAN LANE – INTERLUDE and AN ABSENT FRIEND
• MARK LARGENT – STALLED TREK
• VANCE MAJOR – CONSTAR
• BRIAN W. PETERSON – THE LOST STARSHIP
• BENJAMIN SCHULZ – LORELEY
• GLEN L WOLFE – THE FEDERATION FILES
• RANDY WRENN – DREADNOUGHT DOMINION and other series

Thomas Argante and Nick Cook were newly added to our judging panel this year, although neither is “rookie” when it comes to Star Trek fan films. Thomas has made multiple guest appearances over the past half-decade in fan series productions from DREADNOUGHT DOMINION and PROJECT: RUNABOUT to THE CONSTAR CHRONICLES before launching the new USS CASSANDRA fan series in the Netherlands last year. As for Nick, well, he’s been one of the most recognizable faces in Star Trek fan films dating back twenty years with appearances in the Scotland-based INTREPID fan series, the America-based STAR TREK: HIDDEN FRONTIER series, as well as numerous England-based TREK SHORTS from prolific showrunner Sam Cockings.

Every judge ranked their top five selections in each of 22 categories, with their top choice earning 10 points, second choice earning 7 points, then 5, 3, and 1 points for choices three through five. A judge was not allowed to vote for a fan film they themselves submitted as any of their top three selections.

A huge thank you to each of our judges for putting in their time and consideration to making the Showrunner Awards possible for a half-decade now. You guys are awesome!

As you’ll see from this year’s results, we had a couple of 500-pound mugatos to contend with. In fact, one of these two juggernauts took awards in all but four categories—despite ther dialog being completely in German!

It’s possible that these two powerhouses are the reason that, this year, we had surprisingly few two-way ties compared to previous years—although there were still some—and no three-way ties. Or maybe it was just a coincidence. That said, I’m still pleased to report that 17 of our 23 entries eared at least one award. Scroll to the bottom of this page for a final tally of how many awards each film received. And you can view the majority of the submitted fan films on this YouTube playlist.

And with that, my friends, let’s get to the results of the 2026 Showrunner Awards for Star Trek Fan Films released between January 2023 and December 2025. Links to the winning fan films in each category are provided under that category’s winners. Have a watch and see if you agree with our judges’ choices…

BEST ORIGINAL CHARACTER

Click here to watch FARRAGUT 2024
Click here to watch MIND LEECH
Click here to watch SECOND STAR TO THE LEFT
Click here to watch LORELEY – PART III: ERSTKONTAKT

BEST HAIR & MAKE-UP

Click here to watch FARRAGUT 2024
Click here to watch LORELEY – PART III: ERSTKONTAKT
Click here to watch CAPTAIN SIMIAN’S FIRST COMMAND

BEST COSTUMING

Click here to watch FARRAGUT 2024
Click here to watch LORELEY – PART III: ERSTKONTAKT
Click here to watch FIGHT FOR THE FUTURE
Click here to watch SLIPSTREAM

BEST GREEN SCREEN

Click here to watch LORELEY – PART III: ERSTKONTAKT
Click here to watch THE ROAD NOT TAKEN – PRODIGY RECKONING (EPISODE 4)
Click here to watch FIGHT FOR THE FUTURE

BEST PROPS IN A FAN FILM

Click here to watch FARRAGUT 2024
Click here to watch LORELEY – PART III: ERSTKONTAKT
Click here to watch THE HIVE

BEST SET DESIGN

Click here to watch FARRAGUT 2024
Click here to watch WHAT’S NEXT
Click here to watch THE CASSANDRA EFFECT

BEST SOUND DESIGN

Click here to watch THE ICARUS MANEUVER
Click here to watch FARRAGUT 2024
Click here to watch LORELEY – PART III: ERSTKONTAKT
Click here to watch FIGHT FOR THE FUTURE

BEST MUSICAL SCORE

Click here to watch THE DUMBSDAY MACHINE
Click here to watch THE HIVE
Click here to watch LORELEY – PART III: ERSTKONTAKT

BEST SPECIAL EFFECTS (non-CGI)

Click here to watch FARRAGUT 2024
Click here to watch THE HIVE
Click here to watch SLIPSTREAM
Click here to watch CAPTAIN SIMIAN’S FIRST COMMAND

BEST VISUAL EFFECTS (CGI)

Click here to watch LORELEY – PART III: ERSTKONTAKT
Click here to watch FARRAGUT 2024
Click here to watch THE GREAT EXPERIMENT

BEST EDITING

Click here to watch FARRAGUT 2024
Click here to watch THE ICARUS MANEUVER
Click here to watch LORELEY – PART III: ERSTKONTAKT

BEST CINEMATOGRAPHY

Click here to watch FARRAGUT 2024
Click here to watch LORELEY – PART III: ERSTKONTAKT
Click here to watch THE ICARUS MANEUVER

BEST WRITING

Click here to watch THE DUMBSDAY MACHINE
Click here to watch LORELEY – PART III: ERSTKONTAKT
Click here to watch THE HIVE

BEST DIRECTION

Click here to watch FARRAGUT 2024
Click here to watch LORELEY – PART III: ERSTKONTAKT
Click here to watch THE HIVE
Click here to watch THE ICARUS MANEUVER

BEST SUPPORTING ACTRESS

Click here to watch LORELEY – PART III: ERSTKONTAKT
Click here to watch FARRAGUT 2024
Click here to watch FIGHT FOR THE FUTURE

BEST SUPPORTING ACTOR

Click here to watch LORELEY – PART III: ERSTKONTAKT
Click here to watch FARRAGUT 2024
Click here to watch SLIPSTREAM
Click here to watch BROKEN MIRROR

BEST ACTRESS

Click here to watch THE HIVE
Click here to watch LORELEY – PART III: ERSTKONTAKT
Click here to watch FARRAGUT 2024
Click here to watch SECOND STAR TO THE LEFT

BEST ACTOR

Click here to watch LORELEY – PART III: ERSTKONTAKT
Click here to watch MIND LEECH
Click here to watch FARRAGUT 2024

BEST STAR TREK “EASTER EGG“

1:54 – An exposition/backstory scene which involved creating the TOS Sickbay, finishing DS9 Briefing room and CGI doubles for Dr McCoy and Lt’s Dax and Bashir. All in a one-camera move.

4:00 –  Recreating the “mirror Universe” flag shot from the Enterprise Episode “In a Mirror, Darkly” title sequence, but now as a Khan Empire and all with future ships. Much work for a single still frame!

5:01 – A lineage of Gold Enterprises on the Admiral’s wall in chronological order: 1. First Frontier Enterprise. 2. Cage Enterprise 3. SNW Enterprise 4. TOS Enterprise 5. Phase II Enterprise

Click here to watch TO KNOW THINE ENEMY
Click here to watch THE ROAD NOT TAKEN – PRODIGY RECKONING (EPISODE 4)
Click here to watch FIGHT FOR THE FUTURE

FUNNIEST FAN FILM

Click here to watch THE DUMBSDAY MACHINE
Click here to watch THE CASSANDRA EFFECT
Click here to watch STARCHILD, BUT EVERYONE IS TYLER DUNIVAN

BEST MICRO-BUDGET FAN FILM

Click here to watch SECOND STAR TO THE LEFT
Click here to watch MIND LEECH
Click here to watch SLIPSTREAM
Click here to watch TO KNOW THINE ENEMY

BEST FAN FILM

Click here to watch LORELEY – PART III: ERSTKONTAKT
Click here to watch FARRAGUT 2024
Click here to watch THE HIVE

My congratulations to all of our winners at all levels! Each of you earned the award(s) you won according to a panel of your fellow fan filmmakers. And apologies to those who didn’t win, but my sincere thanks to everyone who submitted.

And finally, assuming that I haven’t miscounted, here are the total number of awards won by each fan film in descending order. As you can see, we had two unstoppable juggernauts, but each is definitely worth watching …

LORELEY – PART III: ERSTKONTAKT – 17 awards
FARRAGUT 2024 – 16 awards
THE HIVE – 7 awards
FIGHT FOR THE FUTURE – 5 awards
THE ICARUS MANEUVER – 4 awards
SLIPSTREAM – 4 awards
THE DUMBSDAY MACHINE – 3 awards
MIND LEECH – 3 awards
SECOND STAR TO THE LEFT – 3 awards
CAPTAIN SIMIAN’S FIRST COMMAND – 2 awards
THE CASSANDRA EFFECT – 2 awards
TO KNOW THINE ENEMY– 2 awards
THE ROAD NOT TAKEN – PRODIGY RECKONING (EPISODE 4) – 2 awards
BROKEN MIRROR – 1 award
THE GREAT EXPERIMENT – 1 award
STARCHILD, BUT EVERYONE IS TYLER DUNIVAN – 1 award
WHAT’S NEXT – 1 award