On the subject of comic books and emphasis.

TyrannoMax & The Warriors of the Core Sizzle Reel

Nothing is final, obviously, it being a sizzle reel.

But you get at least brief introductions to TyrannoMax, BrotoSarah, DeinoSteve, TriceraBruce and PteroDarla, as well as a few choice moments with some of the more fun villains.

Who's your favorite?

Worked up with Vidu Q3 (try it for free, etc) and a ton of built up TMax assets. My YT channel is here.

So, a ways back I talked about Minmax, but I've been trying out basically all the video generators looking for the tools I need, and low and behold this week I find out I've been accepted into the Vidu Artists program now, wherein I get credits and access to access their cooler features in in exchange for... talking about the tech and how I use it.

Well twist my arm. I shall endeavor to be objective and informative despite free stuff (a challenge my spirit needs practice withstanding if anyone else wishes to test me)

So let's talk Vidu.

(outside of being converted to gif, no animations in this post have been cut or edited)

Also, everyone say hi to Maureen the Lizard Queen, every hero needs an evil queen that really wants in his pteruges, and she's that for TyrannoMax.

Vidu's got a bit more oomph under the hood than MinMax (no shade to MinMax, they're brand new and very promising) and it's way too early to be picking winners when it comes to video.

Anyhow, basic features that are nice include the options to upload start and end frames, options for a 4 or 8 second duration (more about that later), and a cleanup/upscale. Credits line up more or less with seconds. 4 credits for a 4 second clip, 8 for an 8 second, and again at upscale. It's straightforward in a way a lot of services aren't.

Apetomic Pyle, done on the fast settings. (not to shabby still, and it gave him monkey legs which a lot of systems balk at)

If you're on the $30/mo tier, you can choose to do a double-cost "quality" over "speed" option. Thankfully, the artist program gets me access. Since there's not yet a seed option it's hard to do a direct comparison, but the quality is going to be a must if you're doing anything that looks like cel. Much cleaner, much smoother.

(4 and 8 second quality gens)

One of the nicest features is the character reference feature. Basically it's like Midjourney's --cref, but with a very strict adherence to character details.

The above images used reference shots of Maureen and Dr. Underfang, and it got the stripes on Underfang's tie right in basically every gen. That's a ridiculous level of character model adherence and, for my purposes, all but essential.

It did misinterpret Maureen's undertail coloration for a sort of fin or drape, but the shot I used was oddly cropped, and sometimes stuff like that happens with gen AI. Given my measuring stick for errors is the era of animation I'm emulating, whatever does slip through is only going to make it more authentic.

There is a limitation in that character-reference and text-only prompts default to 16:9 presently with no options to adjust, but some room to pan is always handy and most people are going to be outputting for phone and not outdated CRT televisions, so, it's understandable it'd be a lower priority feature for the devs.

Walk cycles! By Saint Eniac it's a miracle!

On the left we have one prompted with TyrannoMax's control art, and on the right we have one using that art as the starting frame (4 and 8 seconds, respectively).

Way More details under the fold.

The Secret Origin of Wally ManMoth

Scans from TyrannoMax #26

Cocytus was one of the better-performing comic companies outside the big 2 in the 1970s before the whole company was bought out by Buzby-Spurlock Animation in the early 80s.

TyrannoMax was its biggest title, so almost everyone in the character stable teamed up with the Dinoids eventually.

Process under the fold.

Tribute AMV for Dr. Underfang and Mrs. Natalie Nice/Nautilus.

From TyrannoMax and the Warriors of the Core, everyone's favorite Buzby-Spurlock animated series.

After all, who doesn't love a good bad guy, especially when they come in pairs?

Process/Tutorial Under the Fold.

From this post, a conversation between Mrs. Nice and Dr. Underfang, about how there's more than one way to make a comic.

While the linked post goes into the process in much more detail, the short version is that making a comic with AI involves all the steps of making a photocomic or a Wondermark-esq collage comic.

Here, each panel is a combination of one or more gens through direct compositing and inpainting ('gumby Underfang' is a basic crop-job but the others are multi-image composites, inpainted edits, or both), with graphic design and non-AI composited elements. `

I like to use AI art to achieve forms of 'fauxstalgia', weaving concepts into the aesthetics of artifacts of the past. I consider myself a nostalgia artist (not a nostalgic artist, tho I can sometimes be that), but you can get as experimental with it as you want.

And people are already doing it, they just don't call them comics.

Those sequences of AI-generated photos that tell a horror story that pop up on Tumblr? Those are comics.

We are very much in the "plastic wrap and lens flare" phase of AI art, where the newest and (often literally) shiniest effects take center stage because like an early 2000s kid with a cracked copy of photoshop, it's the new toy.

(I have a feeling Colin Kaepernick is going to give us, at most, a few adventures of a D-rate Borgorroth of Coolswordoorroth before absconding with the bag.)

Feel free to reblog with folks that are doing innovative stuff.

This post is mostly to show off gifs but will get wordy, enjoy this tune while you read.

Did the Academy award me this... award? No. Did the henchmen who have you at disintegrator-point? Yes. And isn't that what really matters?" - Dr. Underfang

One of the ongoing hurdles for any generative AI service is that prompting up something cool tends to take practice yet most people will get frustrated if their first few attempts don't bear at least promising fruit.

The answer: Several Sizes Fit Most

A lot of services, Vidu included, Do this via templates where most of the prompting is already done for you and you just add a few words or an image reference. A menu of these builds up over time as an easy "try out" feature.

I normally don't use those, but as part of Vidu's Creative Partner Program, they gave me about a music video's worth of credits to show their Oscar templates off (full disclosure) and so I'm here to opine.

Wally looks how I feel, like, all the time.

For this one, you just dropped in a pic and whatever it was either walked down the red carpet or accepted a reward in fancy duds. This is all straight-to-the-meme type stuff, but we can still learn some tricks from it.

On the left is the result of using the painted Pizazz Jem & the Holograms character art, and on the right is the result of using the Transformer Steeljaw's animation model sheet.

The more painted and shaded look of Pizazz gives the AI enough to interpret it as a real, albeit very vibrant, person and fills in the blanks accordingly.

Steeljaw, by comparison, is interpreted with all his animation-lines in place, and with the flat coloration, gets reinterpreted as a sort of half-toon or living pepekura creature. Which is an effect you can use by using obviously-illustrated reference with live action backgrounds or prompting.

To produce a particularly unique, dreamlike effect.

But it's not super-consistent across different types of designs. Both the Baroness and Full-Boar here were flat, animation model sheets with no shading. Baroness, however, is more of a person with makeup and costuming trying to make her look like a toon while Full-Boar is a fully cel-shaded toon composited into the scene.

You can control that process more if you're controlling all the prompting, but templates don't really let you do that. On the other hand, all my red carpet pics are first attempts, while the in-scene ones took multiple attempts and tweaks to the process.

And it is surprisingly robust in what it can adapt to, even if Deadeye's doing the 'trying not to shit myself' walk because that toy's legs were purely decrative coverings for wheels, that's impressive.

Sense of scale is way off in hilarious ways, even if one assumes they're people in costumes they're like 2 feet tall.