AI animation -- using Veo

I've been heavily into AI design now for close to two years, and so much is changing. I often ignored AI video generation, not impressed by the final results. But now, it's changing... Veo has taken the next step in quality, consistency, and control.

I started practicing using Veo via the Google Whisk generator, an easy way to generate video, especially animated character styles like Pixar. I decided to try out the 2-month pro level for $10/month (which allows 100 8-second videos per month). Control and prompt cohesion are still major issues; I'd say 60% of the videos I generated were complete failures—not following what my prompts were instructing.

But when it works, it is so smooth and created so quickly; it's worth burning through any credits to finally get that one gem. The hamster Jogging above was one of my first attempts, I was so please by the angle it was running and the camera placement. Once I had a good clip of animation, I started going to Udio for music and Eleven Labs for sound effects and voices. Finally, I wrapped it all up using Adobe's video editor, Premiere Pro.

Understand, we're not talking about major animations here at this point. For the most part, like AI image generation, interactions between several characters are still difficult. Just getting characters to look at each other is sometimes like pulling teeth. Asking for too much in the prompt often results in the AI ignoring everything. Again, when it works...

This second video shocked me—it added every character I requested in the background and more. Udio provided a short Halloween tune, and ElevenLabs provided vocals and sound effects. It's not long nor totally groundbreaking—other than the fact that this took me less than two hours to create a near-Pixar-level group of characters for a 15-second clip.

At this rate, I expect to generate short cartoons of my storybook transcripts by 2027. If I were to try to do this video via 3D models, recording audio, and playing my instruments... I probably wouldn't finish it due to the time it would have taken. Those who are opposed to AI... I understand.

But...
like how Photoshop killed mechanical artist jobs and darkroom photography editing,
like how computers took over how animation is done,
and when music editing went totally digital...
I am embracing this new tool A.I. -- to get my ideas down + to dream of creating things I never thought I'd have the chance to do in my lifetime.

An ARGH! Tune: Strange Signals (Classic New Wave/Dance-Pop)

This one was a blast, especially when everything started coming together. This is my tribute song to The B-52s, which was a fun band with great, hooky songs that were so original and yet also had a Retro 50's/Beach Party vibe and style. Their songs were weird. Their vocals had character.

Strange Signals (Classic New Wave/Dance-Pop)

So when I do these inspired songs based on bands' music - I start with the story. What story can I tell that would seem to fit into that band's playbook (or should I say setlist)? I know The B-52's have done a couple of alien-related songs, and "Planet Claire" is one of my favorite songs. So an alien song...

I thought an alien invasion would be fun, but the twist is they came here to create their own dance club. 

My play on words in this song could go a few ways: 

1.) Aliens are fun and friendly with a great dance club.  -- or --
2.) They are sinister, hypnotizing humans using strange radio signals (hence the screams and moans). There's a third take too.
3.) The singer is possibly attracted to the alien, and the alien is reciprocating, giving her strange vibes, feelings... signals.
Your pick!

**** For those interested ****
I also made a slightly longer version of this song. It's unlisted, so it cannot be seen on my channel, but it can be seen here with this link: https://youtu.be/AixqV-lospM

Created using UDIO.com and Audition for touch-up
Music:"Strange Signals" lyrics and arrangement by Jim Romer

Want to hear more of my songs? Link: youtube.com/@ArghTunes

An ARGH! Tune: Roadside Prophet (Classic 80's Rock)

Inspired by one of my favorite bands of all time, R.E.M., I still remember reading about their first EP in Rolling Stone: the blue-toned gargoyle on the album cover and the praises the critic gave this new group from Athens, Georgia. I soon bought "Chronic Town" and was immediately hooked. 

Little did I know how much this EP album would influence my record collecting addiction. Because of this album, I stopped buying 60's and 70's albums and focused on the here and now with music. Because of this album, I would buy any record I found from IRS Records. Because of this album, I would travel to more obscure record shops. Because of this album, I discovered other like-minded listeners from local college radio stations - the era of college rock.

Roadside Prophet (Classic 80's Rock)

This song is about a wandering figure, a roadside prophet, who observes the world around him while reflecting on change and the passage of time. He walks from dawn to dusk, symbolizing a journey through life and its transformations.

I thought of this character because there is (or was) a similar man in Bermuda who stood by the road and waved to people and cars every day. Local people would tell us how he did this nearly every day after he retired. Everyone who lived in the area knew him by name. Locals said they would talk to him for a while, some bringing him food, water, or a cup of coffee. Tourists would often be seen getting their pictures taken with him. I don't remember his name, but I do remember seeing him every time we passed his standing spot near the main road bus stop. That was so long ago... I wonder if he's still out there.

Created using UDIO.com and Audition for touch-up
Music: "Roadside Prophet" lyrics and arrangement by Jim Romer

Want to hear more of my songs? Link: youtube.com/@ArghTunes

A few words on: Email, Messages and Requests

Just wanted to touch base with those who write me about this blog and with those who make requests for me to create things for them.

• First, thank you for visiting my blog and having an interest in what I do here.

• Second, I don't allow comments on my posts for one major reason: I cannot police or control comments every waking hour of the day. I hope to someday create more picture books for children; I cannot afford to have people cursing, arguing, or making crude comments on this blog.

• Third, this blog's software doesn't have a good messaging system. But everyone is more than welcome to continue sending me questions and comments. I do eventually read comments/emails sent to me from this blog, but... please don't expect quick turnaround responses.

Finally, please do not send me requests. That is not why I have this blog. This is a blog of my random thoughts and sketches. It's a public diary, even though I don't know what I'm going to post next.

I often get requests to post more images of what I do for a living, which is product design. There are too many legal reasons why that's not going to happen. It would be unprofessional for me to show designs that are exclusive to any client. Occasionally, I will post work-related designs, but those are usually either out-of-date or they no longer have any legal restrictions.

Again, thanks to all visiting this blog.

An ARGH! Tune: Muse (Classic Rock)

 This song is inspired by unsung heroes of great music who never made a big name for themselves. Musicians like: 

    • Emitt Rhodes, a fabulous young singer whose albums were compared to Paul McCartney. 

    • The '90s band, Jellyfish, whose fantastic two albums were filled with classic '60s & '70s styles; but they were outshined by the hair rock & grunge movements of the time. 

    • And the better known Marc Bolan, aka T-Rex, whose life came to an all-too-soon sad end with a car crash in 1977. 

Muse (Classic Rock)

This song is about creativity, where the music and words come from when one creates a new song... (perhaps from a legendary mythical muse.) 

Created using UDIO.com
Music: "Muse" lyrics and arrangement by Jim Romer

Want to hear more of my songs? Link: youtube.com/@ArghTunes

Christmas Toon - My Santa for 2024

This year's 2024 Santa image was created via physical pencil sketch, into Procreate for some "pencil setting" inking, and then under-colored and text added using Photoshop. ("BWAAH!" created using AI generating Ideogram.com.)

My wife and I enjoy watching Kathleen Madigan's weekly podcast; she's one of our favorite comedians. She often talks about her touring, including places she visits, foods she discovers, and gifts fans give her at shows. On one particular show, she mentioned a place called The Fainting Goat, where she purchased a small plastic goat figurine that makes that hilarious screaming sound we've all heard in videos. It never fails to be funny, and she uses it in nearly every podcast.

My 2024 Christmas Cartoon

When I do a Christmas cartoon, I want it to be unique. It's too easy to do the usual Christmas gags, puns or traditional jokes. So the goat scream was my influence in this image. Hopefully you can hear that goat scream in your head, (I certainly did as I was drawing it. Never not funny.) 

The original sketch

An ARGH! Tune: When the Night Falls (Upbeat Folk Rock w/Celtic Undertones)

This time I'm going for a more Folk-rock song, inspired by a little mix of The Waterboys, Tom Waits and the Jayhawks. I wanted to have a real Celtic vibe, with a hearty singer and I believe I got what I was trying to achieve. 

When the Night Falls (Upbeat Folk Rock w/Celtic Undertones)

This song is about heartbreak, regret and hope; reflecting on a relationship that has crumbled under the weight of unspoken words and emotional scars. The narrator expresses feelings of betrayal and sorrow, emphasizing the pain caused by a partner′s indifference. The  night symbolizes both the end, and a time for introspection -- evoking a melancholic yet hopeful yearning for a possible rekindling of their relationship. 

Created using UDIO.com Music: 'When the Night Falls'
Lyrics and arrangement by Jim Romer

Want to hear more of my songs? Link: youtube.com/@ArghTunes

An ARGH! Tune: Superficial (Dark synth-pop with post-punk)

This song was inspired by the '80s post-punk band New Order.
It critiques someone for being superficial.
The song was co-created with my friend and New Order fanatic, Struan Grant.

Superficial (Dark synth-pop with post-punk)

At the time, creating a song using Udio meant working with 32-second blocks of music.** After extensively studying New Order's style, I generated 4–6 samples approximating their sound for Struan to choose from. Every few days, we added another 32-second segment, repeating this process until the song was complete.

SIDENOTE: The song’s biggest weakness was the inability to replicate Bernard Sumner’s (New Order’s singer) vocal style. I tried hundreds of ways to describe Sumner’s unique, unpolished delivery but couldn’t capture it. If vocal control technology improves, I plan to revisit this song and update the vocals—though this may never happen if the current lawsuit rules the AI software guilty of copyright infringement.

Created using Udio’s AI technology
Music: Superficial (Dark Synth-Pop with Post-Punk)
Co-created by Jim Romer & Struan Grant using Udio.com
Title by Struan Grant
Lyrics by Jim Romer

As of this writing, Udio.com has improved, now allowing 2:10 song clips, trimming, inpainting (editing sections of music), and remixes (completely reimagining a song). However, I still find that working with half-minute segments provides better control over the music I want to create.

Adventure Time Thoughts

I miss seeing new Adventure Time cartoons.

There don't seem to be as many original shows out there that push the imagination envelope. (Yes, there are shows like Rick and Morty, Hilda, and a handful of other great cartoon series out there. But to me there seems to be a void with new original content from the past 2 years.) As an illustrator and character designer, I'm not watching as many cartoons anymore - we need more Adventure Time-like, Steven Universe and Hilda shows to bring back true imaginative storytelling.

Digital Sketch of a slightly small and young Finn from Adventure Time
using Adobe Fresco and a charcoal crayon setting, with a limited color pallet

I enjoyed the sequel post-shows and Fiona series on Netflix, and feel there is so much more possible with the characters and history of the original. So, I started imagining a prequel series for Adventure Time. We have seen Finn as a baby, and were given several alternative reality versions of Finn. But I was thinking, what about Finn as a young kid, say 8 years old? That's a perfect age where he is becoming aware of the world, but is still not quite prepared to go out and bravely adventure.

I was thinking he'd be younger, smaller, and more immature. The series could explore the origins of Finn and Jake meeting characters for the first time. It could explain the gear Finn found and uses, such as his backpack and iconic bunny hood. (I know some of Finn's past has been explained, but there is still much left untold. At least, I believe there is... MORE ADVENTURE TIME!... please...)

An ARGH! Tune: So Long (Classic Rock CSNY)

This song was inspired by the Crosby, Stills Nash and Young style from the '70s. 

The song reflects on my past, a friend, and the night John Lennon died. 

I was 16 at the time, totally absorbed with music -- as I had been since the age of 12. Any money I was making (or given) was going into buying records (or instruments). 

So Long (Classic Rock CSNY)

Flashing back to a bus ride going home after Jr. Highschool, a friend introduced me to a Beach Boys fan. The three of us would talk of our favorite songs and albums, only to find out we were all complete Beatles fans. From then on, that Beach Boy fan and I hung out everyday, listening to old and new music, dreaming of starting a band and writing our own songs.

Years later, the night of Dec. 8th, 1980, would change the world as we knew it (as much as a 16-year-old could comprehend). I still remember that night. I heard someone confirm Lennon's time of death on TV. It was late. Still, I had to call my friend. 

His mother answered the phone; she was awoken. I apologized, then told her what had happened -- I said I needed to talk to her son. She understood -- I waited as she went to wake up my friend. Minutes later, he picked up the phone confused. She didn't tell him what happened -- so I did, and told him to put on channel 7. We both watched the news, not saying a word for what seemed to be an hour. We both broke down, breaking the rule of never letting someone know you were crying -- but it didn't matter. Nothing did.

I still remember that night clearly. It changed much in me. Changed my view of all things. 

This Dec. 12, 2024, will mark the 10th year of that friend's passing, so these things have been on my mind. Whenever I hear of Lennon being remembered on Dec. 8th, it reminds me of my friend who died so close to that date. 

This song is for you Rich.

Created using UDIO's AI technology

Music: "So Long (Classic Rock CSNY)" — lyrics and prompt arrangements by Jim Romer

Want to hear more of my songs? Link: youtube.com/@ArghTunes

Pop! Boom! Bang! (a Techno-Swing ARGH!Tune)

Here is another ArghTune I did a few months ago.

This time it's done in an Techno-Swing format, inspired by bands like Caravan Palace. This song got over 400 listens on the first 4 days on YouTube; which is surprising since I didn't really promote it or mention it to anyone. I'll be posting more of my AI songs as they get uploaded to YouTube.

My original Techno-Swing song, got many listens on YouTube

Want to hear more of my songs? Link: youtube.com/@ArghTunes

AI Advances: Music!

WOW! Have things advanced in AI music these past few months!

For the past year, I've been deeply involved in learning, using, and putting together AI websites and programs to work for me as a product designer. The improvements are usually amazing and often happen in large leaps. Graphic generation alone has been mind-blowing. It is not perfect, so much is still hit-and-miss.

As for video generation, it is way too new and early -- and I'm not impressed at the overall look of these seconds-long videos. It needs to be less random; currently, there is no consistency. I find it annoying and boring. But enough about that, let's go back to the music . . . 

Okay, here's a song I generated.
The songs I create aren't simply left to AI to fully create. I wrote the lyrics, fully described what I wanted to be included in the song, and generally guided the direction of the song in 32 seconds parts. The best way to describe creating AI music is that you are like a producer in a recording studio, keeping the stuff you like and generally saying "Well, that part's not right -- how about doing it this way instead?" "Add a harmonica solo here.", or "add in a 3-part harmony chorus at this point."

AI Music: ArghTune

My first attempt at doing Crosby, Stills, and Nash song
with a cameo appearance of Paul McCartney towards the end

I'm using Udio which allows developing a full song by building half-minute sections at a time. Udio is currently in beta mode as of this writing, its still free to use, BUT, the $10/month is much more worth the time if you really want to generate your own songs. There is a huge random outcome to most of this process. I find I generally need about 12-32 takes to find the 30+ second clips I want. 

Want to hear more of my songs? Link: youtube.com/@ArghTunes

Google's New AI, Bard - 1st Impression

You might expect a well-known and powerful company like Google to eventually enter the AI competition arena. One could assume that Google has had a major AI-like system for years, used for web searches and information gathering. Or perhaps not? My first impression of Bard, Google's response to ChatGPT, is, "Holy $#%&! This might be the worst AI I've encountered in over a year!"

Let me explain the level of detail I usually expect. As a toy designer, I use AI to help me collect images of toys, conduct market research, and explore styles and color schemes, among other things. Recently, a client requested generic toy robots but wasn't sure about the exact appearance. This is where AI shines, by generating images/mock-ups in a variety of possible styles.

A very traditional cute metal toy robot design - requested in metallic silver without colors

Another variation showing different flocked materials and some color accents

Above are two examples of robot toy designs, created by Dall-E (also known as ChatGPT-4).

I find Dall-E to be the best at "listening" to exactly what I'm asking for in my toy design prompts. Many other image generators tend to overlook key details mentioned in the prompt. Now, let's look at what Google's Bard created. Note: This was done using the exact same prompts I used with Dall-E.

Google . . . I'm speechless. (Was this thing shot in the chest?)

This one's even better. And by "better" I mean worse.
Why the colors? Why does it look old, grimy and used.

These things would give nightmares to the Island of Misfit Toys. They do look as if a child created them. The colors are so muted and conflicting. If AI was involved with these designs, I'd like to know how it came to this point. Personally, I feel Google shouldn't have released Bard to the public. They should have kept it closed until their technology was at least on par with the AI world a year ago.

UPDATE: My Top 10 AI Images of 2023 - - - - - - - - - - - #1 Moldy Bread Monster

- - - - - UPDATE - - - - -
Needed to update with the latest version of the Moldy Bread Monster. All AI generators have been updated several times since the creation of the first image -- so this is now the latest version circa January 2024. I mean, this newer guy is actually made of BREAD! The former dude was more wool-like.

Love, love, love this updated version. Much better mold.
The goofy expression has a very Adventure Time/Gravity Falls vibe.
The red veins in the eyes are simply priceless. Bravo, AI -- Bravo!

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 

Originally posted on 12-22-2023

NOTE: These images were not arranged in any level of greatness or priority. I’m gathering the 10 images I feel represent my best AI results in 2023. I hope you find them amusing, interesting, and inspiring too.

Behold, the slice welding Moldy Bread Monster

Meet the Moldy Bread Monster, born on the day there was a half loaf of moldy bread in our kitchen, and I REALLY wanted a sandwich! (Hate when that happens.)

The MidJourney prompt was simple, though I added the word “dancing.” The dancing wasn't quite captured, which often happened with version 4 back then. But the character's uniqueness, especially with it seeming upset about a slice of “good bread” in its left hand gave me a good laugh. (Especially since I was in a similar situation mere hours ago, complaining and holding a “bad slice’ of moldy bread.)

Runner-Up AI images of 2023

Here are a few of the AI images I generated during 2023 that I felt were interesting enough but didn't make the top 10. 

Manic Santa Claus was a popular trend during December, this one was my weirdest

Using someone else's prompt, I edited it to portray Billy Elish as a warped version of the Poison Ivy character, (mostly picked her because she used to sport green hair.) This came out much better than expected.

Red Sonja fighting a gigantic viper creature

This one came out of nowhere! I believe I simply asked for a "Vivid Colorful Santa Hat" for photos of pet costumes. I have NO IDEA why this was the image I got instead. Disturbing.

Another disturbing image, this was "a photo of Humpty Dumpty circa 1910."  

A beautiful fantasy city scene. I especially like the warm lighting in the foreground and the insanely doom-inspiring details of the towers in the distance.

My Top 10 AI Images of 2023 - - - - - - - - - - - #10 Darth Vader Worn Revisioned

There used to be a great website called Illustration Friday. Every Friday, a new word was given, and artists would submit images based on that week's word. For the week when the word was "WORN," I chose to interpret it as "damaged and shabby as a result of much use." Using this definition, I depicted Darth Vader as worn out from a long day. Many years later, I uploaded that image into Leonardo.ai, activated the 3D settings, and received this result:

In less than 20 seconds, my 2D drawing was transformed into a 3D version. The only disappointment was that the smoke trails from the lightsaber looked more like gray wood with stones. However, the Darth Vader character turned out very well, with excellent lighting, reflections, and textures.

The original sketch was digitally drawn within an hour and posted on the Illustration Friday website.

Sometime later, I hand drew the design using brush pens, Copic markers, and a white Gelly Roll pen.
This was the image uploaded into Leonardo.ai to be revised by AI technology.

Baby New Years 2024 - The Year of AI

HAPPY NEW YEAR!!!

Every year around this time, I recreate versions of my original Baby New Year character kicking in the new year, which I created 10 years ago in 2013. It has always been very popular among visitors to this site, and it definitely gets stolen by MANY people who download other's artwork to call it their own and sell it online.

This year, something a little different: I'm using AI to create Baby New Year based on my original drawing.  

Behold, the AI-generated version of the 2024 Baby New Year

To be honest, this little guy was a combination of 4 AI images, which had to be altered, assembled, and touched up -- so it probably took me much longer to do than simply draw a new illustration. 

The first Baby New Year image from 2013, using brush pens, a Gelly Roll pen, and Copic Markers

The original concept pencil sketch in 2013

My Top 10 AI Images of 2023 - - - - - - - - - - - #9 Cthulhu According to AI

In his famed novel, Call of Cthulhu, H. P. Lovecraft describes a statue of Cthulhu as:

"A monster of vaguely anthropoid outline, but with an octopus-like head whose face was a mass of feelers, a scaly, rubbery-looking body, prodigious claws on hind and fore feet, and long, narrow wings behind."

I prompted his exact wording into Leonardo.ai and generated several dozen images following that description. All of the images generally had similar aspects, but the level of difference was totally unexpected. Next, I entered more prompts, but this time provided much more details about character placement, size/proportions, and the background/environment setting. Which produced this:

This image above instantly became my favorite image of the group. Cthulhu's size in the far distance, the foggy air, and the mysterious shielded warrior, such fantastic visuals generated in one image. 

More prompted images of Cthulhu are seen below, seen in ranges from traditional to insectoid.

My Top 10 AI Images of 2023 - - - - - - - - - - - #8 Joker Circa 1910

A nice feature of AI image generation is that you can suggest creating an image set in a specific period. For example, imagine if the Joker fought Batman around 1910. AI tends to do a better job with individual characters than with multiple people in one image. This is often because when describing several people in text, AI can lose focus on which person should receive specific details, leading to a tendency to morph two or more characters together.

[Sidenote: If you’re interested in what inspired the character Joker, check out the silent film “The Man Who Laughed”; a truly eerie depiction of a character that would influence comic book/movie culture for decades to come.]

Fabulous sepia toned image of the Joker back in 1910; the expression alone is priceless

Here are some samples of attempts to depict the two characters in a 1910 fighting scene. Note how Batman often appears more manic than his classic stoic expression. It's as if the Joker is wearing the Batman costume. 

Additionally, Batman's armor is too technically advanced to represent his costume accurately in that timeline. Apparently, it seems AI is pulling reference to the Batman’s costume mostly based on the more modern Batman films instead of the cloth based costumes in earlier times.

My Top 10 AI Images of 2023 - - - - - - - - - - - #7 Celebrity Not-Quite-Right-Look-A-Like

To me, nothing is more impressive than when an AI program successfully captures the likeness of a famous person. However, AI companies are now striving to limit this aspect of image generation due to the growing threat of Deep Fakes in multimedia. If left unchecked, this could lead to worsening political scenarios, increased legal actions from celebrities regarding the misuse of their likenesses, and a general rise in public deception, fueling falsehoods and conspiracies. This could potentially lead to complete anarchy in a world already susceptible to misinformation.

This image doesn’t quite look like Joey Heatherton, but it captures the style of her time.
The green smoky background, black dress, bobbed hair, and mystic pose makes this a fantastic image.

Most American-based AI sites, tend to not do great exact likenesses. They do permit likeness usage generally as a reference in prompts to generate similar-looking characters. But if referring to anyone famous in your prompt, the censorship restrictions are usually maximized. (This is not true from many foreign AI sites, especially those based in Japan.)

In this particular case, I referred to a lesser-known celebrity from the early '70s who I saw on TV all of the time on variety, talk, and game shows as a kid: Joey Heatherton. (Not only was she cute, sexy, and bubbly — she was the inspiration to Catherine O’Hara’s character, Lola Heatherton, one of my all-time favorite comedy shows, SCTV.)

Catherine O’Hara as the over-the-top-manic-laughing, Lola Heatherton, on SCTV in the late ’70s
Yes, that's Catherine O'Hara, known for Home Alone, Beetlejuice, Best of Show, and Schitt's Creek.