Midjourney Token Bashing, Nano Banana, and Weavy with Marco Isle

Rory and Drew invite creative polymath Marco Isle to do what this show does best: break Midjourney in interesting ways. It’s a token binge from shadow play, moonlight, GOBO shadows, datamosh, pixel smear, prismatic rainbow light streaks, and androgynous beauty plus where --exp actually makes images better (and where it ruins them).

They also crack open token bashing (smashing words to birth fresh visuals), show why aspect ratio is half the art, and steal moodboard fuel from Cosmos.so.

Then it gets dangerous.

Nano Banana enters the chat, turning one still into dozens of consistent shots with plain-English tweaks. They compare video stacks and frames workflows (Veo-3, Kling, keyframes), talk Weavy automation, and use a real “Book of Jonah” case study (42 scenes, ~5k images) to show how fast this all moves (and where it still breaks).

It’s Midjourney’s magic, but with receipts.

Keywords: Midjourney tokens, token bashing, EXP settings, aspect ratio, mood boards, Cosmos.so, Nano Banana, Weavy, frames, keyframes, Veo-3, Kling, AI image generation, Midjourney video, consistency, creative workflow.

---

⏱️ Midjourney Fast Hour

00:00 — Cold open + guest intro (Marco Isle)

00:35 — Marco’s background: design → UX/UI → fashion

04:48 — Aesthetics vs. mechanics; the cooking/technique mindset

10:50 — “Rome Reimagined” + early Frames testing

15:59 — Token bashing & Marco’s custom GPT flow

20:59 — Favorite tokens: shadowplay & moonlight

21:32 — New token: gobo shadows (why it works)

22:19 — Glitch looks: pixel smear & datamosh

23:34 — Prismatic rainbow light streaks (stacking ideas)

23:54 — Androgynous beauty as a control aesthetic

25:22 — --exp sweet-spots (3, 7, 10, 13)27:17 — “Liturgical drift parade” prompt set

30:24 — Why Aspect Ratio is everything

34:12 — Idea sources: mood boards + Cosmos.so

38:54 — Nano Banana enters the chat (workflow + why it’s different)

42:15 — Case study: Book of Jonah (42 scenes, ~5k images)

43:03 — Video models: Veo-3 notes + start/end frame

43:33 — Weavy & automation; setting guardrails

50:00 — NanoBanana pros/cons; real-world limitations

52:51 — Frames: Kling vs others; aspect-ratio flips

55:11 — Aspect-ratio workaround (whitespace expand)

57:47 — Keyframes consistency test (the car roll)

---

LINKS:

Nano Banana—Image Gen Documentation: https://ai.google.dev/gemini-api/docs/image-generation#prompt-guide

Marco Isle on X: https://x.com/ai_artworkgen

Marco Isle on Gumroad: https://markisle.gumroad.com

Drew's 1% Midjourney Style Guide: https://dcbruck.gumroad.com/l/Midjourney-Course/ib3nsqs

Episode Transcript

(00:00):
What's up, everybody, mid journey fast hours podcast
episode 49, Drew Brucker, Rory Flynn, and we've got a special
guest today, Marco Isle legends only and Marco's one of the O
GS. I would say also been deep into
mid journey, been deep into AI image Gen. for, I don't know,
forever since I've first seen your name pop up on X.

(00:23):
And we're excited to have you here today, man.
So, so welcome. Why don't you just sort of give
a quick introduction of yourselffor those that aren't familiar
with you? Hey, thanks very much, Drew.
Yeah, so like you said, I mean, I've I've kind of been doubling
with AI stuff starting with mid Jenny, obviously, but the OG for

(00:46):
about like three, 3 1/2 years. And yeah, like, I kind of just,
I started just messing about on online and just posting really
because there's, because there was so many things to discover.
I was kind of just posting like an online journal for myself.
And then people were kind of digging the stuff and it kind of
just snowballed from there. You know, like I always try and

(01:08):
stay true to what I like it rather than like going with, you
know, just noise. Like, so if I want to do like
fashion stuff or whatever it might be, I kind of just stick
to that, you know, and then I just post and, and share
findings because obviously there's a million things that
are possible and it's just nice to kind of put it out there.
If it can help other people, great, you know, And that's,

(01:32):
that's kind of weird, really. What's what's your what's your
origin story too with like the interest in AI image Gen. like
what's your background like thatmaybe connect some of those dots
or was it just totally different?
You found this and you're just like, oh, this is a brand new
thing that's. Like something I didn't.
Know I cared about. I think so.
So I've got background in like graphic design, user experience

(01:54):
and interface design and fashionas well.
Like I, I basically designed baseball caps and T-shirts and
they used to like have several websites like selling third
party brands, you know, online. And I actually got into like the
digital space just by setting upa shop on eBay back in the day.

(02:15):
And I was annoyed at how shit I was annoyed at how shit the
listings looked when you, when you added your products.
I was like, OK, if we make the listings look nice, can I charge
more for said products or can I get more and like, it's like
going into a store that's like peeling walls and all the rest

(02:36):
of it, unless that's the vibe. But like, you know, you're,
you're a bit sketchy and a bit unsure about parting with your
money. Whereas if it's like really nice
and rapid, it's marketing. You know, it's one O 1.
You can have you have a really shit product and market it
amazingly and do really well. You can have an amazing product
and market it poorly and it doesn't sell, you know?
So it was kind of, I always love, which is why I kind of got

(02:59):
into UI and UXI love aesthetics and mechanics, how it looks and
how it works. And I think they go hand in
hand. Oh, I love that we talked a lot
about a mechanics on here with with the AI image Gen. right,
with the prompting sort of like mindset you have to have
especially early on with the models, right.
It was almost like it was hard to get things without describing

(03:20):
them mechanically. So.
I think that's an. Interesting.
Yeah, Word that you use there. Go ahead, Roy.
Now, I'd say, Mark, I had a question for you.
On a on a scale of like 1 to 100, what's your creative ADHD
levels? I'm pretty pretty high up.
Pretty high. Up I think we're all sort of in
that I think that's why we like find each other because we just

(03:42):
know that like is or anyone that's basically in the space,
right, Like if you don't have some level of creative ADHD or
like curiosity, I don't I don't think you know for people who
don't know Marco or haven't beenfollowing him, he does great
stuff on AI. But some of the other stuff that
you've done is super cool too. Like I remember you putting
together some magazines. And stuff like.

(04:02):
That you do, you know, product design, you're designing
T-shirts, hats, things like thatalso.
But we we just talked about thisbefore we got on Marco likes to
cook a lot. So, you know, some of the things
that he's dreaming up in the kitchen, that's just, that's not
because we have AI tools, that'sbecause we have creative, you
know, we have a creative on hereand a creative mindset.
So dude, I just like I said, I really like how you sort of like

(04:26):
bridge all of that energy out there creatively and put it into
the AI work too, because you cansee it a lot of times.
And remember some of your stuff early on that I saw first was
like the, the, it was like fashion and like the Greek
Acropolis with like the, you know, the graffiti.
And it's like, there's more layers than just like, give me a
woman in like a fashion pose. There's like a lot of intention

(04:48):
behind it. Yeah, that's, that's, that's
well said, man. Like, yeah, I think there are
there's so many depths to what we do and any kind of like
everyone, everyone has really interesting backgrounds that
they draw upon to like bring into into the mix when they're
kind of like exploring. And I think, you know, we all
know that mid journey and and other image and tools, but

(05:10):
mainly mid journey because obviously it's the OG are all
visual things, right? So you, I mean, when I'm, when
I'm kind of doing stuff, I'm, I'm not just typing stuff in and
then iterating without looking at what I'm seeing.
Like I see something I like or like, Oh, that's cool.
I didn't mean to do that, but actually that's quite cool.
I'll start like going off in that direction.

(05:31):
It's just, it's a visual thing that you can kind of just
navigate and it's, it's really nice.
You know, it's like, it's, it's very similar to cooking.
You know, you, you have a recipelike that you follow, but it's,
it's more about technique because if you know how to make
a cake right, you can change theflavors.
It's literally that like once you know the technique and the

(05:52):
process, like the structured wayof organizing prompts, you can
then swap out the angles or the parameters or you know the
lighting or whatever it. Might be, you know, let's roll
the tape. There we go.
All right, so we're just taking a look at Marco's stuff here
where you were talking about some of the stuff that he's put

(06:13):
together. So he's got some of the stuff
here, right Marco? You've got sort of like I guess
some, some prompt collections, but you've also got the prompt
magazine stuff that you were doing too.
Is that different from from this?
Yeah. So the Prompt magazine was a
collaboration I did with free pick for the first upscale

(06:34):
conference that they did in Malaga.
So we just did a magazine as like a little goody bag thing to
go with the with the show, whichwas a nice thing, you know,
because like in this digital age, it's so nice to actually be
able to have something tactile to to flick through.
It's great, man, that was that was really cool.
I remember you showing me sort of like the layout and stuff and

(06:56):
I was like, this is like this iswhere it looks cool in hard
copy. Like it looks it's not, you
know, it's like getting mid journey magazine or or the, you
know, like the special edition book.
Yeah, digital version, Yeah, that's great.
Yeah. We've actually got, sorry, we've
actually got an extended versionof our PDF which I can send to

(07:16):
you sort of that magazine. Yeah.
And if there's a link, if there's a link to that, let us
know. We can include that in the show
notes too, for folks. Yeah, I was looking at this.
You've got this. And then, you know, obviously
good follow on X. That's your primary channel,
correct? Yeah, like to be honest, like
when I saw next, I wasn't, I wasn't really posting on

(07:38):
LinkedIn until like probably earlier this year.
I've just been kind of doing stuff on X It's so funny, like
looking at my feed in white because I've I have my, I've got
a dark mode on my screen. I.
Know. It pops so much to giving you
the. White.
Yeah, I know that's I'm like switching browsers all the time
and it always defaults to white.That that shot there Drew is.

(08:01):
I started doing a whole, yeah. I started doing a whole lot of
thing around mythology and that mythology meets a metropolis,
like, really cool. Like, kind of like all these
characters, like thrown into like New York or, you know, just
quite cool, cool content. I like the dark gritty vibe too.
Yeah. What, what I like about both of
you is I can always look at the images and know exactly who it's

(08:25):
from, which is like after, you know, there's like a, there's a
lot of exploration and stirring,like, you know, straying from
the mean. But like, also at the same time,
like I know a Marco image. I know it drew image when I see
it. Like if I didn't see your
handle, I'd know it's you. Because if there's like a
there's consistent themes just like sort of baked throughout a
lot of the content. And I know it's like, you know,

(08:46):
a lot of the stuff that you do in the angles and sort of like
the exploration. And then Drew as I can tell
right away, like I know Drew, I know a Drew image out of nowhere
like you could you could put that in a line up.
I'd be like, that's true 100%. But it's cool, man.
Like the metropolis like that, that mythology metropolis.
It seems like a lot of that sortof baked into what you're doing
overall. Is that?

(09:06):
Is that something like What? Why that?
Well, so going back to what you were talking about previously,
like the the graffiti kind of like Roman columns and stuff.
So I basically when when frames first came out, I run my frames,
they asked me to do some like testing prior to, to launching.

(09:28):
And I really like the idea of like I called it Rome
Reimagined. So it was like taking all of the
elements like I could think of from ancient Rome.
So obviously the architecture, the clothing, the environment,
you know, all that kind of stuff.
And actually then bringing it into like 20 first, yeah, 21st
century. So and I did like MMXXV, that

(09:52):
was the thing. So it was like 2025 and you
know, like looking at, I did AI did a whole bunch of like
plinths with marble sneakers andstuff on them instead of like
Roman busts and like graffiti columns.
And then looking at like having the togas but having it like
camouflaged, for example, instead of just normal silk.

(10:15):
Just really experiments with that.
And then, yeah, like, I loved that.
That was another one, actually. The girl with the horns, You, if
you go. Well, that's part of it, Yeah.
If you click into that thread. So she's got like, golden horns
basically. Yeah.
That one there. Yeah.
I kind of just started doing these.

(10:35):
I've got a really cool prompt that I was using and.
Yeah, man, I made a few mood boards and then just like this
prompt seems to just open up allthese really cool things.
Yeah. Can we start to petition?
Can we start to petition mid journey to get multi prompting
back? I know you like.

(10:56):
I don't understand, I know they changed their architecture right
for when they did V7 onwards butI actually did my last PDF
series on gumroad. Is actually on prompt stacking
or multi prompting and you, you can really get some interesting
stuff because you're, you're kind of fusing multiple ideas

(11:17):
and directions and then weighting them in different
ways. And like, you know, obviously
you guys all use seeds and you fix the seed to, to test things,
but like just fixing the seed and then like weighting things
one way or another when you, when you have two or three
stacks. So interesting.
I, I really like it. You can you can get some amazing
stuff. You can't I don't yeah, it's

(11:38):
interesting to like to hear and and wonder what other people do
inside of mid journey with with waiting in general, because I
have always found that fascinating.
You know, with with image and style ref too, you know, just
like how you can dial those in, you know, and just get, you
know, completely different results or even just blending

(12:00):
right and waiting. And you know, it's just there's
so many different variations of a single idea or or sort of like
workflow within mid journey to get unique results just by
dialing in the weights, I mean. It's mental.
Yeah, it's it's, it's probably pretty wild.
What's your what's your like here?

(12:20):
Here's a mid journey question. If you're going in there, what's
the what's the feature that you're using the most?
Are you using mood boards? SRAF multi prompt.
To be honest, like I, I actually, again, I did AI did
another PDF on like how to recreate SF without using an SF,
just using natural language basically.

(12:41):
So I mean, I wouldn't, I don't use SF that much.
Like obviously they're very powerful, like when you use an
image as a reference or whatever.
But yeah, I, I kind of just likeseeing what I have from my, from
my prompt. And I actually, I, I built a
tool which I think I've, I've run some stuff that you sent me

(13:02):
Rory through to like extract thetokens.
Oh yeah. Basically I was, I was it's like
the fifth version of this tool that I've been like playing
with. It's like a custom GPT basically
drew. And yeah.
So like obviously it does like you can, you can upload an image
and it does like a gives you a decent prompt and then like a

(13:23):
structured breakdown as well. And then I was playing with like
this experimental thing where you like fusing some of the
words together because obviouslyan LLM doesn't look at text, how
humans look at it. So I, I got some really, really
interesting results by doing that.
And I, it kind of gives me 5 like sent like very short
sentences fused together as one prompt.

(13:45):
So I can run that as a whole thing.
And it's almost like prompt stacking without prompt
stacking, like without waiting. And then you can like take out
each individual statement and then run those as well.
And you get other stuff. Just endless, endless.
It's awesome now. Like it's, it's really like,
that was the first thing that I noticed with it when I was you,
when you were sending me the prompts back and it was like,

(14:06):
you know, I was getting these, these crazy like term.
It's like term bashing, right? It's like almost like blending 2
images but with like blending 2 tokens.
I remember it being like gettingsomething that was like a like a
Jaguar or something I sent you. And.
Apex integration or something islike one word and I'm like, I
don't know what that means, but it's cool and it worked and it
gave me some really crazy stuff.So again, we we've talked about

(14:29):
a bunch of prompting techniques on here, Drew, I don't know if
we've ever mentioned sort of token bashing.
Yeah, I don't think we have. I don't think we have.
And I was, that's kind of what Iwas looking for because I know
you posted something on that. I probably was a while back, so
maybe we can pull it, I don't know.
Do you, is it, is the GPT something that like is far

(14:52):
enough along that you want to show here or is it still work in
progress for you? I mean it works fine but like
it's just not public but I can Ican show I can show you if you
want like how it works. I love these.
I love these too. These are great.
That's actually with Rev even I wanted, I wanted to say Reeve,

(15:13):
that's how I was. It is it Reeve or is it Rev. No.
Well, I would say Reeve because of the E right.
But it's actually like. Apparently, like here's an
example, right? Exactly bashing, right?
Like these these sort of words that just are two words that
form one word, right? It's exactly that new word,
right? Yeah.
It's kind of dope. I've never really played with
that concept before, but I thinkthat's a really cool thing.

(15:34):
And so, you know, like Roy, we've talked about a lot of
things on this this podcast to the point where it feels like
we're always like, oh, we've talked about this before, but
this is this is, I think this issort of like one of those novel
things I haven't seen before. One of the one of the other
things as well. This is a while back, but I was
I'll see if I can find it, but it's because it was quite a

(15:55):
while. I think it was last year.
But literally some of the words like we I was just trying to
work out like illumination and enlightenment or whatever, like
like putting them together, say like illuminitement or whatever,
all these kind of different things.
And some of the results, man, were like insane.
Like I did a like a provocative forest kind of thing.

(16:17):
So it was like I was like provocate provocation.
But the end bit sort of occasionwas like illumination as well.
Like there's like it's just light and Eroticism and all
sorts of cool stuff that's really interesting.
It's really interesting. I find that kind of stuff.

(16:38):
It's just it's untapped. I think David was saying from
mid journey he was basically saying that not a lot of people
use the advanced stuff at all, the waiting, which is why they
kind of what 2 bothered about it.
But yeah. But it's fun because that's the
creative piece of it. That's not the control.
That's the like let mid journey be mid journey do its own like
wacky stuff and you end up with really cool things because.

(17:01):
But it's also like the creative part on both sides, right?
Because it's like that's not really something that Mid
Journey would have thought to door promote.
It was, it's something that you thought about.
That's the sort of like new idea, but then Mid Journey can
execute on it creatively as well.
So it's kind of like this combination.
That's just pretty cool. Because it still is the only
tool that to me that allows you to be that creative and not have

(17:25):
to force control. You know what I mean?
Like it's not about force control, it is about just like,
let me smash 2 random words together and maybe this will
make something cool. I, I do what I love do.
That was like one of the, when you showed me that, that was the
first time I had seen anyone sort of thinking that way.
And even for like instead of it being like even in the prompt

(17:46):
structuring thing. So like, again, for anyone who
doesn't know, we're talking about like the GPT that Marco
built. Like when it spits out the
prompt, like it, you know, it's in a structured fashion.
But instead of it saying like subject and then like colon and
like this, like I saw it up in one of the things before it said
like Metro Muse, like that was like the name of the subject,
which like instead of naming it as subject or environment or

(18:09):
whatever, it was like utilizing like a token as like a holding
category, which I was like, all right, cool.
That's another little like tip. Yeah.
And The thing is, The thing is with that tool like so you can,
you can basically put in like a Pinterest image or whatever it
is, like a reference image you like.
Then I was kind of like putting my own images in, so like you

(18:35):
kind of just continually evolving and just going down a
complete rabbit hole with like seeing what it would, seeing
what prompts and tokens it wouldgive you from reinserting images
created from the prompts and tokens they've given you
previously. It's like insane.
OK, so I know we got a lot to talk about today, but I am
curious like, you know, I like you've, to me you're always like

(19:01):
talking about tokens and I thinklike this, you know, token
bashing thing adds another levelto it.
Do you have any general favorites that you like at the
moment, or that you're experimenting with, or that you
just always go back to time and time again?
I mean, the one you, you actually did a post the other
day which I replied to about shadow play.

(19:23):
I mean, that's one of my favorite things, shadow plays.
I mean, Rory, Rory loves a bit of shadow as well.
And it's it's just awesome. Like just just that really like
high contrast. You know, I actually did a whole
PDF on shadow play as well and just playing with the different
types of shadow. You know, there's like that.
I love dappled dappled. Dappled is a good one.

(19:44):
You know, you know what gives amazing lighting?
Moonlight. She put in moonlight as a token.
It's insane. Haven't tried that.
What have you tried? Gobo shadows.
Gobo shadows. Gobo Shadows.
Is a good. Open up mid journey run gobo
shadows I I need to know what that is I've.
OK, so go gobo shadows would be like something like this.

(20:10):
OK, so it's like it's an object in front that's got the shadow,
right? So let me see if there's.
Any one of these and no, that's you.
Yeah, like Gobo shadows. Yeah, You know, simple prompt.
I was I was actually like beforethis I was like, what are you
know, what are some like tokens that I haven't talked about on

(20:33):
here before? That was one that I that I like.
I mean, you can use that for obviously not for portraits, but
I'm always thinking in a large way just with like portraits.
Think the other ones that I always there, there are a couple
like really cool ones recently that I found like pixel smear

(20:56):
and data mosh effect. So I think this one, I think
this is a data mosh effect. This is, you know, and this is
not a, this is not a complicatedprompt, right?
I mean this is like super simplestuff, but I I really like the
effect of stuff like that. I've been doing quite a lot of

(21:19):
glitch stuff as well, like with like but like you try fragmented
bodies, that's pretty cool. OK, yeah, let's run.
Let's run a few like random things I always like to like.
You reminded me of one the otherday, which was chromatic
aberration. I just love that.
That's always a good one we can do.

(21:40):
Let's let's do some other ones. Let's do oh, another one.
I, I, I run a lot. It's like just weird core.
Like when I'm doing like the thestyle reference, the style code
exploration. Weird Core is kind of a cool
one. Try try prismatic rainbow light
streaks. OK, I like, I like where this is
going. Prismatic Rainbow.

(22:04):
All right. Prismatic Rainbow.
Yes, this is what we're talking about.
This is the sauce. Yeah, I mean, like there's, I
mean there's just so many good. There's just so many cool things
like this where it's like if youthrow that in there, it changes
the entire image, you know? You could do like, what was the

(22:28):
other one I had? I mean like colours and stuff.
You could do pale monochrome palette as well.
It's quite cool. Or like I really like.
I use androgyny a lot, but I like how that is like neutral.

(22:49):
Yeah. Androgynous beauty, for example.
See, there we go. That's another good one.
And I, of course, I never know how to spell it, so I always
have to do that. Yeah, dude, there's a there's a
lot of good ones. I just, I just found this, I
just found this prompt from Marco that we used a while back

(23:12):
and there's so many good ones inhere, like just just even the
token bashing and like the random ones.
I'm like. Let's.
Never come come up with this. What was that other one we just
saw that was on your feed too? It was.
What Metro muse? Metro.
Metro Muse. I mean, and look like this, I
think we're just going to run this token, right.
So this is not in combination with anything.

(23:33):
This is, I guess, more or less going to just show us kind of
like the results of what we're talking about here using Exp at
all, Marco. Yeah, I do.
But I find lower ones give better results.
I find the higher you go, it kind of just like makes it very
almost like stipple glazed, verydotty.
I don't know if you've seen thator not on your experiments, but

(23:54):
I tend to do like 3713 and then like 20-30. 737 All right, Yeah.
27. Welcome to that.
Podcast. We're in it, baby.
This is it. This is the stuff.
Fragmented bodies. And of course, like, so this is

(24:14):
different too because it's got my personalization.
So this is all this stuff's going to differ slightly for
everybody, right? But I think this will be kind of
cool, just like look at the likethis.
Almost like camo, isn't it? It's like camo.
Yeah, it I'm, I'm really findinggreat.
Yeah. Like between I would say 0 and
10. Like just breaking out of this

(24:35):
box of no Exp. I typically almost always like
the four grid better with some Exp sprinkled in.
Look at the. I mean, see what I mean?
Like. Always works.
Weird core. Wow, well, see, I hear Oh,
that's there's some you. Know.

(24:57):
Look at there. There we go, prismatic rainbow
light strips. All right, so now we know.
We can, we can. But you imagine, imagine that.
Imagine that. Stacked so that prismatic
rainbow light streak, stacked with like cinematic fashion.
Or, you know. Go go shadows with a prismatic
or prismatic rainbow. Yeah, yeah, There you go.

(25:18):
Smash that together. Like that?
Pixel smear. Pale monochrome palette.
That's OK. Look at the texture on that
flower. Very nice.
That's something I never thoughtI'd hear you say.
Hey, you know this is what we dohere.
I know how you feel about the flowers.
That's right. I did.
I did a whole load of religious kind of stuff.

(25:40):
But like, cool, cool, religious,not like, you know, in your
face. Yeah.
Yeah, like, I mean like these are.
I've never I've never heard thisterm before.
Liturgical drift. Whoa, OK.
And it and it was like it was like priest and I did it with
like motion blur. So it was like priests like
floating with motion trails and stuff.

(26:01):
It was pretty cool. Let me see if I can find.
That look at this, then Metromuse, yeah.
It's good. Yeah, it's cool.
There's some there's some fun ones even just I was looking in
here. There's so I have so much like

(26:22):
random like random tokens from this prompt.
Like which one? Let me should I share it just to
just to show the actual prompt itself just to share it?
Absolutely. Share it.
Yeah. Yeah, this one cuz I I was I was
digging this one when we were using it, it was just like and

(26:43):
it was, let's see layered composition text box levels I.
Like I like primal gaze. Right Shadowhunter Apex glare.
That was a good one. Ritual Fang like they're
editorial beast primal. You know, we have the ritual

(27:05):
profile hassle and medium format.
Unparalleled precision. I I sort of like that
combination. I use high precision a lot, but
I like unparalleled precision too.
I mean, there's so there's so many like tribal iconography,
Obsidian etched fur. Like etched fur is a good one
too because a lot of times that's just like, or velvet
depths. Velvet Depths.

(27:27):
Velvet Depths. Feral whisper like these are I
will I love that kind of stuff because I'll play with that all
day. Obsidian sculpt, you know like
these are it's fun. It's.
Fun, that's why. That's why the mid journey
coherence is special. You know, they have a little bit
of that magic just sprinkled in there, You know, where if your

(27:49):
model's too coherent, it just kind of, it's not going to do
anything. Yeah, yeah, it's it's pretty
insane, but you know, I'll stop sharing this one now.
That was just like very cool. I remember that prompt
specifically for having like sent me on a rabbit hole with
those words and didn't just likeripping.
It was like the multiverse in there.
It was like it's taking like oneword and going this way and

(28:10):
this. Way, this way and this way.
Yeah, it's really fun to play with on the tokens.
I still think that's like the biggest exploration, Like
there's so much. Symphono yeah, I sent, I sent in
the chat that liturgical Drift Parade, the prompt and also the
link to some of the images I created with it.
It's like literally one of my favorite image set that I've

(28:32):
done. It's so nice.
I'm gutted out to do this. No views.
What aspect ratio you think I should put this in 4-5?
I did. I did 69 actually.
OK, let's try. 69 I'll do 69 and4/5.

(28:55):
That's that's another thing actually talking about aspect
ratio. Literally just adjusting you're
doing permutations with aspects like the same prompt just
changes so much depending on theaspect ratio you.
Did so much it's. It's probably one of one of the
most important parameters, aspect ratios of the whole
thing. 100%. Yeah, there's, there's

(29:18):
definitely biases baked in basedoff of that and the training day
that's in it 100%. Yeah.
And obviously, like if you're doing like a cinematic shot
should be probably more landscape and versus like a
close up should be, you know, orfive or whatever.
Oh, yeah. So here's here's your results
here through the Yeah, sick. Yeah.

(29:40):
Got it. So nice.
Now, Drew, if you had a, if you had a gun there, now we got a
whole, We got a whole crossover between.
Yeah, we do. We got a collab.
None with a gun baby. There's you want to know which
one I've been I've been liking alot aspect ratio wise 1/2 so.
1/2. I know a lot of people don't

(30:01):
generate in 1-2 probably, but it's been really good for like
like cropped vertical composition like really like
really solid, like asymmetrical,unbalanced, like no symmetry at
all like it's. I was doing like 321 as well at
one point. Yeah, it's, it's just taking the

(30:21):
wider angles and just making them.
It's like 916, but 916 sometimesis already almost too structured
based on probably the data that's input from 9:16 so.
It's like, yeah, exactly. Let's make it thinner and let's
see what it comes up with. It's.
Great. Oh no, this is.
Cool, it looks awesome. Awesome.
So I ran this with some. I ran this with some mood boards

(30:43):
on. Just now.
Yeah. Oh yeah.
Yeah, it's. Yeah, this is.
Yeah, this is this is sick. That one there top left as
you're on your screen now, it's really cool.
Yeah, yeah. These, all these all have a a
story inside of them. Yeah, it's very cool, man.

(31:06):
I love I love motion. I really do.
That's probably one of my favorite things, motion shadow
play. And then just like I love the
juxt juxtaposition of things. I like the the whole Rome
reimagined. So you have like this ancient
Rome. In fact, one of the prompt
stacks I did was like, I took some of this kind of motion, you
know, like light, light streaks and all that kind of stuff.

(31:29):
And I did a Roman soldier with light streaks and then like PVC
avant-garde editorial fashion asdifferent stacks.
And I, I weighted them differently.
And like you, you get like PVC busts of like Roman soldiers and
then like, cool stuff, man. Yeah, really cool.
Hey, tell, tell me this like I, I, I think probably people are

(31:52):
curious and I, I'm curious to like it.
It's, we all probably have different ways we go about it,
whether it's intentional or not.But when you're say, say that
idea specifically, right? What's the trigger for that
idea? Are you finding something with,
is it as simple as you finding something that's, that's Roman
and then all the sudden you've, oh, why not pull this into an

(32:14):
urban environment and then it starts to snowball.
Do you see a particular token and something that you've
created before, inspiration froma past image, and you're like,
oh, what if I use this in a different type of environment?
Do you use LLMS to brainstorm? Like what?
What is your creative building process look like for idea
generation? So many, so many layers to it.

(32:35):
Like, so when I, when I was younger, I used to literally
just sit and mess about with Photoshop and layers and like,
I, I used to make my own little look books with like fashion
stuff and just messing about with, with all the patterns and,
and that kind of stuff. So I'll always be really
interested in colours and, and, and that kind of vibe.
And yeah, like we all love looking at visually pleasing

(33:00):
images, you know, like, and one thing, I mean, obviously a lot
of people use Pinterest, but there's, there's one that I go
on. It's called Cosmos.
I don't know if you've heard of it.
Cosmos dot SO really cool. It's it's basically like
Pinterest for designers. Rory, you'll absolutely love it,
mate. It's so good.
I'm looking it up right now. It's.
Insane. It's got a good, it's a really

(33:21):
good curated mood board type feel to.
So like I've got a lot of influences from the stuff I was
doing previously, like with the fashion stuff.
I've always loved camo and I andI always like graffiti and St.
wear and that kind of stuff. But I think, yeah, like I think
when you see, when you see a particular image, it kind of

(33:43):
like sometimes gives you an ideaor like sparks.
I'm kind of inspiration and likeeven my own images as well.
Like I'll, I'll kind of iterate on them and say, oh, that'd be
those two things together. Would be actually pretty cool to
split them together. And then I've had this whole,
yeah, that's actually really nice as well.

(34:03):
I had, I had this whole thing oflike trying to mine the perfect
prompt basically, which is why Istarted messing about with like
custom GPTS and just documentingstuff, you know, and trying to
see like how can I improve my process?
Like obviously we all can promptand you know, we all have like

(34:24):
ideas of like doing things and you can tweak the parameters and
stuff. But how can we like elevate that
by like diving into not only thework that we create, but then
looking at, you know, influencesand then putting those into the
acting tokens and then messing with them.
It's, it's infinite, right? It's just, it's an iterative

(34:45):
process that will probably neverend.
It's just an ongoing creative journey, which is, is awesome.
And like, it's like fashion in itself and, and, and general
style, like everything recycles,you know, like stuff that was
trendy in the 80s now becomes trendy again in 2025.
And, you know, people pull like animal prints into fashion or

(35:06):
whatever it might be, you know, so by very much like, it's, I
probably approach image creationthe same way I approach food.
I, I work with my eyes, you know, you, you kind of see
what's cool and then you kind ofgo with that.
Put the ingredients on the tableand then just be like.
What can I do with this? It, it feels like, it feels like

(35:28):
a reps thing too. You know, just like with most
things, it's like if you're, if you're doing this, you know,
the, the more you do it, the more ideas get unlocked, right?
Because you're, you're kind of like breaking outside of the
box. Over time, you're finding more
and more ways to utilize this ordo that and it just opens more
doors and you find different pathways to go down, you know,

(35:48):
versus if it's more of an infrequent thing or you don't do
it enough. Those things just aren't going
to click. Exactly.
That's amazing. That was really cool, that one
there with the NFL guy that you just went past.
Yeah, that's. Are you running a lot of this
stuff in on mid journey video too like when you do it?

(36:08):
Or is that just like a like an apple?
I have done some stuff, to be honest.
I've run some stuff I forgot I run as videos and then I went
back. I was like, shit, that's
actually like insane. Yeah, yeah.
What about? Prompting hole and then it's
just before we know you have like I'm just generating like
1500 images and then like bang, like I did like 100 videos in

(36:31):
between, but I forgot about thembecause I did, you know, 700
images after I ran it. I know that's this is the
problem with the. Problem.
Here you go. Here's some more tokens.
Motion smear. That's a cool one.
You know, just just cool stuff, guys.
I mean, I, I think people love tokens too because I think
again, like you can utilize 1 token and that could generate

(36:53):
and spark an entire hub or new idea that that maybe somebody
jumps into. So I, I think that's really
cool. Haven't seen.
Roboscopic pulse light. That's exactly the work that's.
Yeah, haven't, haven't seen that.
NFL me do with RGB spectrum trails.
Nice. Yeah, some cool stuff.

(37:15):
Cool stuff. What we're I mean, look, there's
so many image models, video models now.
I mean updates change because they're coming every week.
Maybe the prioritization of these things change work.
Like what are the tools that you're finding yourself using
the most right now on image and video?
Maybe you like, is it again, of course, like maybe it's just use

(37:37):
case based, right? What it what is the outcome of
what you're trying to do? Is it for play?
Is it for more of a client? You know, like maybe that alters
it, but like, what are you, whatare you sort of like falling
back on at the moment? I think like you said, it's
dependent on what you do right? Like I think my default is just
like mid journey for explorationbecause nothing even comes close

(37:58):
to it. Forget it, never will.
It's just game over. But like, so the stuff that I
did like that metropolis mythology stuff, the original
images were created in mid journey and then I pulled that
into nano banana, right, which is this whole new workflow.
So that's actually something I really love doing.

(38:19):
And I I did something else that I showed Rory, which I haven't
shared yet, but it's it's basically called where petals
fall. And it's like, the idea is like,
it's this volcanic kind of wasteland, really black with
like black soil and like a few spindly like yellow wildflowers.
And instead of raining normal water, it kind of rains petals.

(38:40):
And then this woman emerges fromthe soil, this black soil, and
she's wearing like a yellow, bright yellow dress that's kind
of in the same vibe as the petals and the flowers.
And then she has this kind of like romantic exploration of the
of the landscape and she kind ofnavigates her way up to this
like stone tower. And she's kind of like shots of
her hand on the stones and withholding to be care flowers.

(39:02):
And then she kind of like times up to the top and holds them up
to the to the stormy sky and kind of lightning strikes and
then the pedals fall and it justkind of goes black.
So that's my vibe And I I did some shots on mid journey and
then I just created literally like about 100 like insanely
dope shots in nano banana and like I was doing them in LM
arena, which was painstaking, but because it was so.

(39:25):
Yeah. Am I going to get it?
Am I going to get it? No, no.
OK. I got to run it again.
Ron, I feel like the more times you selected nano banana in a
session, the more it was shown bizarrely, which was pretty
cool. But yeah, I only, I only stuck
at it because it was so good. The results, I was like, I don't
care, I'll wait. But then then obviously when it
got dropped into free pick and and all these other tools, like

(39:47):
I literally did about 100 shots in like 10 minutes, I was like
shit. OK, I feel like this is the
perfect segue then, because we we knew we were going to talk
about this. We knew we were going to get in
a nano banana. This feels like a good time to
do that, right? I know we've all three been
playing with it and some of the some of the most recent stuff on

(40:07):
your ex profiles showcasing thattoo, right.
So let's let's jump into this right now that it's, you know,
not just accessible through LM Arena and we can access it
directly. I mean.
How is this changing the game for you?
Maybe from a workflow perspective and maybe also just

(40:30):
from like a what's possible perspective.
I mean, to be honest, like, again, like I shared, I don't
know if you saw it or not, but Idid like a cinematic reenactment
for the book of Jonah with PJ about a month or two ago.
And we were doing that from likeJanuary till April, May, it was

(40:52):
like 42 scenes, 15 shots in eachscene.
It was like I probably made like4-5 thousand images minimum on I
actually used Google Imogen for that because it was had pretty
good consistency. But even that like we had to
impaint like so many shots. And so that workflow, like
literally if we had nano banana would have been cut by 10/15/20.

(41:17):
I probably do that in a day mateI reckon.
You want that hour of those hours of your life back
instantly. But then on the flip side of
that, I love attention to detail, so it was kind of
annoying me that it wasn't perfect.
So I was trying to get it good and but it's just crazy, like in
that period of time, how quicklythe tools changed, like from

(41:39):
what we had available, like VO3 wasn't even released, man, like
text to video. We actually did our whole
prologue for that video, for that film with VO3 text to
video. But yeah, it's just, it moves so
fast. I think you obviously have like
a core tool set that you go to, but it, it would be silly to

(42:01):
just sit on your laurels becauseI mean, like Rory's been doing
with Weavey, like some of the stuff he's been doing, like
automating processes, because I think that's where it's going
now. Now that pretty much
everything's possible, especially with nano banana.
It's it's not really, oh, oh, can we make this?
Yeah, you can. You can make whatever you want,
but what do you want to make? And it comes down to more like

(42:21):
people's style and their taste. I think now more more than
anything else, obviously storiesreally important throughout,
always has been even, not even AI stuff, just in general.
But yeah, I think automation andall the tools we have available,
you kind of spoil it for choice.Yeah, yeah, you almost have too
many options, right? So many and it's, you know, I

(42:44):
think that's where that's definitely where I find myself.
I put this in my last like stagepresentation.
I'm like, I showed like a littlediagram of where each thing
could go and what you could change.
And it was like, you know, this image can go here and then it
become another image or it couldbecome a video or it could
become a 3D asset or it could become a piece of code or it
could become text. Then from there you can change
this and this. I'm like, that's like the

(43:06):
infinite multiverse. And that's where if you're don't
have some like guardrails or some sort of like limiting fact
factor, you're just gonna, you're gonna end up not getting
anything done. That's where, that's where we
get, that's where we get in trouble.
Like, yeah, it's like, oh shit, we what do we just spend the
last hour or two doing, right? We need some guard rooms.
I've talked to companies about this too.
I'm like people that are implementing these workflows and

(43:27):
these pipelines into their into their agency, into their brand,
to their business. I'm like, you know who you also
have to train? Not the creatives, the people at
the top who are making decisionsbecause if they just keep
saying, well, what about if we put it here?
What about if we change the color of the dress?
What about if we do this? And it's just like, they also
need to be like, refocused, like, no million.
Because you can make a million edits doesn't mean you should

(43:50):
make a million edits. Sure.
Yeah. Like, because that's the bane of
all existence. Anyone here listening from an
agency, you know, point of view,you know what I'm talking about.
It's just like, what about if itwas a little bit brighter
outside? What about if the guy was
wearing earrings instead of a necklace?
What about if, you know, it's like too many because it's all

(44:10):
possible now, so we have to or else nothing's gonna get done
like. 100%. It's, it's crazy though.
I'm sure Marco, you felt a lot of that with the with the Jonah
project. Man, like some, some of the
shots, some of the shots I made,I'm genuinely like really happy
with. Like they look so cool.
There's there's a shot where. I'm going to go pull that up

(44:30):
while you're talking about it here.
I need to see if I can find the actual thing.
But basically there's a shot where the the whales kind of
like spat Jonah out back into the ocean and the fishermen have
noticed it and they kind of likego into the water and kind of
like cradle him. And there's a shot of two
fishermen holding him and he's like limping their arms.
It's just such a nice shot. Like honestly, when I made it, I

(44:51):
was like, that's so cool. So like for context, Drew, we,
we had like a, a proper scriptwriter and, and I trained,
I trained a GGPT on. So we had the script, we had
custom prompt that I built. We had about 10 different

(45:11):
characters plus all of their outfits.
We had about 5 or 6 locations from like the King's bedchain,
but like the, the seaside, the the port, the ship deck, the
ship, like quarters underneath, like some credible stuff and.
That was not done before. A lot.

(45:31):
It's like I'm not. It's like bad now.
But that's the crazy thing with longer production cycles now,
like for these longer pieces that people are doing, it's like
if you spend a month and 1/2 on a project, like by the time
you're done, you're like, I wantto go back and redo the whole
thing because it's so much. Easier.
Yeah. See, that's the thing that kind
of drives you nuts. But at the same time, right, you

(45:54):
know, that's where it's like, man, when you talk to other
people in the space, you feel a little bit less bad about it
because everybody knows that. But like, you know, when you try
to describe to somebody that's not, that's where it kind of
hurts you to say, Oh my God, like, this tech is old now, you
know, but this looks really good.
I'm just sending you the the post where with the shot I was

(46:15):
talking about, there's four shots that I really like in
that. It's this is this was when did
you guys release this? This was or July that.
Was yeah. But you guys were working on
that since when that was a couple of.
Months. January, yeah.
Wow, yeah. That bomb spot, right?

(46:35):
So sick. Love it.
So for anyone who I know is not listening to this podcast, who
might be listening for the firsttime and think that AI is a
magic button, there you go. Six months.
That's a that's a typical production schedule for 5000
images to start. Like that's just your portion of
it too, right? I mean, that's like like a lot.
That's the same thing as reshoots.

(46:57):
The same thing is it's all the same.
It's just a different, differentmedium.
Great stuff. Right, like.
Yeah, I found it. I mean we, we actually built out
with Imogen like all the all thecharacters like.
Literally. Prompting I prompted like dry
linen, wet linen, all these different things, you know, just

(47:20):
to like. Get the different.
Vibes for the outfits and the costumes.
Different lighting. These are great stills.
I love this eye that that one's.Great.
Yeah, basically the king is having a premonition, and that's
like the whale's eye. Yeah, I'd sack.
Not bad. It's awesome.
The, the biblical content is like so prime for a, it's like

(47:40):
so perfect for AI, you know, like it's 'cause it's, it's also
like how you want to interpret it.
Like everyone's got their own interpretation of the stories
anyway. So it's like just visualizing it
in a way that looks cool. It might be different.
Like, yeah, is it a good job with that?
The The funny thing is PJ did this like I don't know if you
saw it was like mocking all of the like biblical stories.

(48:02):
They did like a something went crazy viral.
It was like Jesus in in the tombwaiting to get brought back to
life from God and stuff. I don't know if you saw his,
It's really funny. It's so he's got.
To Knack at that, he's got to. He's got to Knack at that stuff.
It's really good. It's crazy.
Yeah, this is, I mean, so let's let's circle back to Nano Banana

(48:23):
specifically, right? I don't.
Maybe some of the the folks listening to this have already
played with it. Maybe some haven't.
What are the what are the thing like?
Let's let's go to the things that are really changing the
game with this. Why is this such a big deal,
right? And then let's talk about sort
of like maybe even some of the limitations that we're currently
saying. You know, I think that might be

(48:45):
a good place to go. Totally.
There's, there's so much like for I'm jumping in on this one
because I've been trying to playaround with context and flux
context and runway references and ChatGPT and they all have
their own limitations. Flux to me is flat.
Like I don't like flux because it, it looks flat.

(49:06):
There's no depth. They it's really hard to sort of
bring that or like take that saturation down and take that AI
look away from it. So like, to me, flux has always
been like utilitarian, but not great runway a little bit
better, but it also it's sort oflike has its limitations in
terms of what it can do. And then there's, you know,

(49:27):
ChatGPT, you can't do 16 by 9. You can't do, you know, 9 by 16.
You have to do whatever the, theaspect ratio is.
They're all three. 232. Yeah, and it's, and you know, it
can be really good, but it can also just be really bad and flat
again. And as we said, Drew, it's it's
all yellow and green. Yeah.

(49:49):
So all these tools have been, you know, mid journeys.
I feel like oh, ref has gotten better, but this is this is next
level. Like this is like you can take
it into a scene. Like I don't know if you've
tried some of this stuff with ityet.
Yeah, like if you have a still like let's just say it was that
girl. Like I tried it with something
the other day where I was just like, keep the same exact image.
You know, let's let's swap it toan 18 like an 18 millimeter wide

(50:11):
angle push in closer. So like the field of the field
of view is still exactly the same, but the, the presence of
the person is bigger. And it just went right in,
didn't change anything. It was like I was in a 3D sort
of like space like this. That's crazy, you know, or if
you do the, you know, or if you do the like I was shooting a
room and it was a room, you know, sort of eye level

(50:33):
composition of the entire room. And I was like, give me an exact
overhead of this and it just flipped.
And the dimensions were perfect because I ran it through key
frames in frames and like it went from that sort of like eye
level view and like traveled up to the overhead look and like
nothing morphed. Meaning all the.
Dimensions are perfect, right? So it's like that's that's what

(50:56):
we're talking about. I also have a good example of
this with the car that I just. Shared earlier do do you guys
have a preference on the video model for start and end frames
clean one? Now thing things really good,
yeah, like obviously VOV O3 you can't, you can't do starting in

(51:16):
frame of VO3. So I'm hoping they're going to
sort that out soon. Surely they are going to, but
it's it's a bit frustrating because you can obviously do
start from VO3 and it's amazing.But yeah, like the the stuff
I've tested on cling's pretty, pretty impressive.
Yeah, yeah, right. Hey, Rory, go ahead and pull
your your video up and I'll kindof walk through because this is

(51:37):
a this is a really good example here, right?
Like you can create this starting image, right?
And doesn't matter where it's from.
I think all of us like to go to mid journey.
But then you've got sort of again, going back to nano banana
here, very natural language prompts to up make the update or
the net new image or whatever itis, right.

(51:58):
So I'm guessing this is what youused in terms of like fortune
beneath herd. Like, is this verbatim, like
what you did with this image as the image ref?
Yeah. And so, you know, it's like,
again, that consistent character.
There's no Laura involved. You know, I think there was.
How do I get to the rest of these?

(52:21):
There we go. Oh, OK.
I see. I see.
I see. But this is all from this one
image, I guess is the. Point SO.
You know, and this is, you know,again, very simple, you know,
prompt variations where you'd beproud of me.
I kind of threw mine into a figma I was doing around here,
but like same thing, right? You get a starting image and you

(52:42):
know that like I I love the consistency with the colors
right of the but you know, let'sadd a backpack.
Let's have him, you know, let's change his facial expression.
Let's change him smoking a cigarette.
Let's change him, you know, walking back to the house.
Let's remove him from the scene.Let's flip the camera angle to
the other side. Let's do a aerial shot side

(53:04):
profile, right. Let's add a car.
Let's you know, let's have him play on the phone with the car.
Let's have him smoke a cigaretteon a car.
Let's have him hold big stacks of money on the car.
You know, like up to you know, like whatever.
But I mean like this is this is this type of stuff though,
right? That wasn't really all that
possible unless you kind of wanted to utilize Chachi BT,

(53:25):
which again kind of then takes you back into this.
It's not. Doesn't feel quite.
Yeah, doesn't. It's a one image storyboard.
You just you just did A1 image storyboard.
Right. So it's it's it's super, you
know, it's super cool. That's kind of what I was diving
into with that, you know, and I think there are some limitation.

(53:45):
I think the one limitation I raninto too was aspect ratio, which
I, I think I've, I've found a answer for which was just like,
if you've got maybe like one of these is a 11 and then let's say
you wanted to change it to A169.I mean, you could obviously do
that in mid journey. But if you wanted to stay in

(54:05):
tool, you know, I think you could act you, you could add
white space on either stylus to 16 and have it fill it in,
instruct it versus saying changeto A169 because it I was
getting, I was not getting any results with that.
Apparently you can. Let's say you've got a two by
three image and you want to, like you said, you want to make
it 69. You can literally upload a 69

(54:28):
empty frame and it will do it. Right, right.
OK. So that's what I'm saying is
like it's just like, but if you just say it without providing
that negative space if it doesn't like that was 1
limitation, I think like the other limitation was in Gemini.
If you're doing this, it looks like a little bit low, lower

(54:49):
res. Maybe it's a compressed file is
what I was kind of saying I. Don't know what's going on there
cuz the LM arena stuff was like insane when?
It was, yeah. And then it.
Was like a little bit like did they did they just release like
the the fast model is that what this is versus the like the full
quality model, which I don't know why they'd hold back on
that unless it's really expensive, but you know, it is

(55:10):
really fast. Like that's another thing that
we should mention here. Like it's fast, like.
It is. Fast like 2 minutes like this
thing is like a couple seconds. Really good.
It's good. Oh, and you get one.
Yeah, you get one image that takes minutes.
Like to the point where you don't even want to stay on the
screen, right? I did, I did a shot.
I did a shot which was like it was.

(55:32):
So I basically uploaded a reference of a guy and I had AI
recreated this like pickup truckand the shot that I wanted was
like this guy driving like in the like driver's seat of a
Porsche. But you just see like the
dashboard and kind of like his POV.
I managed to get his reflection,just the top bit of his hair in

(55:53):
the wing in the rear view mirrorand all that kind of stuff like
it's so good it's ridiculous. Just by saying it showed show
the inference of his head, top of his head in the rear view
mirror. Done.
That's. Awesome.
Let me we're going to pull this one up so you can, so everyone
can. This is a good test in terms of
consistency. So like to see actually how

(56:15):
consistent it is. So if you've ever run key frames
before, you know that if the twosubjects are different, you'll
have morphing like if the if thedimensions like you know, for
this specific shot, like if the dimensions for the car, if
there's let's pull an example here.
So like if this is if this is a different size, if this, you

(56:39):
know, rear view mirror is in a different place.
If the spoiler is a different shape, like you'll get morphing
for key frames. So this is like a good sort of
like barometer test to show thatit's like, OK, this stays the
same even as it goes to an upward sort of format, right?
Like everything stays the same even if we go down.

(57:00):
Like the wheels stay the same, everything here stays the same.
Like the lines on the side of the car stay the same.
The exhaust pipe stays the same.It morphed a little bit there.
But again, like, this is pretty much like 95% consistency to get
something like this, which is insane to go like, all right,
let's go get these angles and turn them into key frames.

(57:20):
Because amazing. It's it's interesting, like with
the with the where is my weevie board?
I'll pull this up. And with that, Rory, right?
Like you're trying to shorten the gaps of these frames, right?
So that there's less room for interpretation between those
frames, correct? Correct.

(57:40):
So it's also like keyframes again, if you have tools that
can actually do the keyframes, which is great.
Now like that are that are actually like handle it from
scene to scene. The hardest part is the
consistency. Like if a character's beard is
two different sizes and you wantto go from keyframe to keyframe,
like you'll see the beard like grow in.
Real time, yeah. Shrink or grow?
Yeah. It's like you need and like

(58:01):
keyframes is like ultimate control in terms of like start
and end. But you know, taking this and
then like starting to batch process also like this is this
is nano, but like on a differentscale, right?
So we're showing like the regular scale.
And then this is like sort of what we can do from like a batch
processing system where this is a little tip for anyone, right?

(58:21):
Like to start with nano, don't like it's not just the single
image like if this was the original image I created in the
journey, right? Like this standard image now if
I want to create all different angles or different shots of
this car in different environments, they're like it
has the frame of reference of the front three quarter view,
right? Like it has no idea what the

(58:42):
back of the car looks like. So if you're trying to do like,
you know, shots from behind or whatever, it's always going to
be different because it doesn't have any frame of reference.
So like if you're going to try to take one subject or you know,
something like a product or a person, I think this is just
like a useful sort of idea is totake that one image and then
turn it into like a get like sort of the rear view of it, get

(59:04):
the side view of it and get likea rear three quarter view of it.
Like with, you know, whether that be a person, a product or
whatever. So you have the frame of
reference for each side of it first before you go and iterate
a million different ways. Because if you're looking for
like extreme consistency, of course, this is on like the, the
more like professional side of things versus like just the
creative side. You know, because we, when we do

(59:27):
this, right, I'm building littleprompts that are essentially
saying like, take this car and just turn it to, you know, turn
this into 3 prompts, one for a side, one for a rear, one for a
rear three corner. Like this is all the prompt is
saying with the reference image.Keep this exact car in this
exact environment. Change perspective to side
profile to side angle, right? Nothing crazy.
I don't understand how it like made like how does it know what

(59:49):
the back looks like? Like it's so good.
It's just interpreting right andlike it fits, like it fits the
lines, it fits the design style.Like it just, it's nails it,
which is crazy. And then, you know, taking it
here and then basically iterating like front shots off
of this, off of this image. So using this image as the
reference and then we can get like 5 shots of the front of the

(01:00:11):
car. You're doing the same thing for
the rear of the car variation doing, you know, same thing for
the side view and then doing same thing for the rear three
quarter panel view. So.
Again, we're using like a lot ofdifferent tools, using a lot of
different system prompts here toget that done.
But like, it's crazy because I'm, you know, I'm testing it

(01:00:31):
with other cars, right? Like we use the the BMW.
So it's almost like core your, your core image, your kernel,
then you've got these these the short listed number of pillars,
right? So in your case, you've got 3
and then it's the big waterfall after that because you've you've
filled in sort of this, I don't know, let's just call it a

(01:00:53):
panoramic 360 view of what this car looks like.
And now because you have identified fully what this car
looks like, it can go out in up,down, right?
So it's almost like I, I'm looking at this like there's in
the image up top and like it like this is horizontal.

(01:01:14):
I'm almost thinking of it like vertically.
It's like the image up top. Then you've got this second
layer, then you've got, you know, sort of all the
iterations. Pyramid after that.
Yeah, pyramid. Yeah.
There you go. Because then even more complex
stuff, right? Like this?
Is an. This is an easy image, right?
To play with like, that's not aneasy one.
But. There's a lot of things in that
translucent. Yeah, you could see a lot of

(01:01:35):
things in there. Amazing.
So it's able to do this and it'sable to sort of take that and
run with it. Like even just getting, you
know, some of this stuff is impressive, right?
Like it's getting the coils, it's getting the the
translucence, getting the gears in the front, the tire, the tire
consistency, like the treads. I mean, it's so impressive with

(01:01:56):
this stuff that I'm like, damn, like this one messed up here.
It's the only one out of 20 thatit really didn't really didn't
mimic. Yeah, I was going to say like
what's the, you know, are these pretty much 1 shotted for the
most part, yeah. So this is First off, you know,
again building a right here. If I was to just run this

(01:02:19):
workflow again, all I'm doing isdropping in this image.
I'm not prompting anything like this is automated, right?
So. If you change the image
basically. Yeah, just change the image.
This will then turn into three different shots.
Then it'll upscale. Then this will get routed to
here to get basically changed, varied five ways, varied five
ways, varied five ways. It's the same exact workflow,

(01:02:40):
just duplicated 4 times. Like this is the same exact
thing. Prompts to LLM to split to
different images prompt to LLM to split to images, right?
So it's not, it's not crazy. But like here in the prompting,
if I wanted to like I just gave it a shot list.
That's what I'm starting with. Just like perfect front view,

(01:03:00):
macro, wide angle, close up, wide, high, you know, wide and
high. Same thing here.
If we're going from the side view, you know, super wide, low
angle, close up, Dutch tilt. So I'm giving it just a shot
list of what I want. You could also automate this
with an LLM if you wanted to. I was just giving it what I
wanted. I'm literally thinking, I'm
literally thinking like, I wish I had this for Jonah because I

(01:03:21):
bet you could apply that to likea shot list for characters, you
know? Literally the character one.
This one will this one should this one should really help
everyone see sort of the power of this stuff.
Cuz this is, this is where I, you know, when, when we're
talking about our creative or like creative direction for

(01:03:45):
professional versus like having fun, you know, like this, you
need like certain control, right?
So like here, this is like building out like, you know,
controlling each aspect of the character, just like having a
little section for it. The same way you might break it
out into like a modular prompt, but you know hair and features,
body type, age, you know ethnicity and gender, right?
Hey, zoom in a little bit, Rory.There you go.

(01:04:07):
You. See this?
Yeah, so we have age, we have hair and features, body type,
you know, style. So we can create like a base
character, right? And it's like, all right, we can
just sort of choose. We can run this to four
different image models to see which one produces and then roll
from there. You know, down here we can put
essentially like a section of like clothes.

(01:04:28):
So we can like art direct the clothes, right?
Where we have this can be swapped.
What this is doing is just saying describe this clothing in
detail. So we have an image and a piece
of text that's sort of supported, right?
And you can swap any piece of the clothes if you want to top,
mid half, lower half. And then we combine them all.
We combine the images of the people and then like the prompt

(01:04:50):
itself to sort of create the guyin the clothes.
And once you have like the one image right, of like the guy in
the clothes, then you just go and vary it.
So here I was using, you know, in the same way as that car.
It's just basically saying like,all right, generate 6 more
prompts for this guy in some sort of environment with some

(01:05:10):
sort of rules prompt structure. Basically saying structure like
this every time run it with the LOM so it creates all the
different views, right? So I can basically do like an
entire. Fashion campaign.
Yeah, this. Guy right, like this is and
that's one way because we can. Also if H&M are listening.
Yeah, yeah. You know, I'd throw it into a

(01:05:32):
storyboard format, be like alrighty shot list whatever you
want. Character doing it that way can
also test like a different character with different looks
to see how they want. So you know all this stuff can
happen and relatively one click.All I'm really doing here is
inputting of character features and the clothes, and there you
go. Yeah.
And like you push, you push, go,the rest of it happens.
That's amazing. That's a little workflow's

(01:05:54):
changing by the month over here.Dude, this is I'm so addicted to
weevie it's insane. I, I gotta, I have to cut myself
off sometimes or else I'll be, I'll be just totally in the
rabbit hole, just like. That's so.
That's so cool, though. The stuff I've seen you share on
Weavey is like amazing. And I've been tapping you up.

(01:06:17):
I need to, I need to dive into it a lot more because I think I
think when you have like creative ideas and when you
like, there's like like you said, there's different things.
It's like dabbling on a personalkind of just vibing with stuff
versus I've got a project like Jonah, for example, using that
shit is next level. That's that's that's how you

(01:06:39):
like automate stuff and and get things done so much quicker.
And but like, I think the hardest part of everything is
the setup, right? Because once you, once you have
the setup and structure, you can, like you say, drop in a
different car, drop in a different person clothes.
That's what it's all about. Yeah, so like.
That right, like if you can control the character, then you
think about doing the same exactthing for the environment, think

(01:07:01):
about doing the same exact thingfor a product.
It's like, OK, and then you can composite it in there and then
sort of another another thing I found relatively awesome, by the
way, just just for anyone who's still hanging around and you
know, thinking about video stuffyou can like with VO3
specifically, like I can cut outlike that guy like if he's just
in like in a position like remove the background and just

(01:07:21):
like paste him in a scene without having to like re light
it or restructure it or anything.
So just like 2D flat guy in scene and just like type what I
want to happen and they like immediately integrates them in
like the lighting like so it's it's like simple things like
that. Sometimes it's like I don't have
to go and create the whole base image with the character.
And the same and everything. It's like drop it in and just be

(01:07:43):
like a guy walks to the right and it just like he
automatically sort of picks it up so it won't recognize that
but let. Me I want this is the.
Last thing I just. Going to say I need, I need how
long is it going to be? Because I I really need to.
This is it, just so everyone cansee there's a structured way,
and then there's how Drew and I make our.

(01:08:03):
Shit, leave this. This is this is the full like
brain on like total OverDrive. Like let's just go in a million
different directions. So everything doesn't have to be
structured in here either. Bro, I'm going to start sending
you outfits for my caricature. I can put it on now like you
know, we have all our variationsof of our characters.
My gosh. Stupid text, right?

(01:08:24):
So that was all I wanted to showis that like it doesn't have to
be like this structured workflowand like there is, there is like
the freedom to just go wherever your weird brain wants to take
you in there. Yeah, yeah, well, yeah, let's
wrap this. Let's wrap this baby up, Marco,
man, Thanks for thanks for hopping on last notice to like
we, we enjoyed having you man, and give this guy a follow.

(01:08:46):
We'll we'll link some of the stuff too that we can.
I'll, I'll, I'll include some ofthose links to and, and send me
over anything. I'll I'll make sure to include
it in the description. But yeah, dude, keep up the
great work. Amazed by all the stuff that you
come up with. I mean, you're you're one of
those I think that always createjust real high quality things

(01:09:06):
with whatever tech is currently available.
And you know, the quality that is available, you're always
achieving at the maximum level. So props to you, man.
Keep up the great work and thanks for joining us.
Roy, you want to say anything? Before we go.
So annoying really. Cool.
Yeah, I'll, I'll come back whenever you want.
Come back and hang. Yeah, dude.
And keep keep creating just justfor no agenda creation purposes.

(01:09:29):
The stuff you put out is awesome, and it doesn't.
That's the best thing. That's the best thing.
Best advice for anyone else heretoo.
So Marco, appreciate it man. Thank you for coming.
For anybody who's still hanging on, if you haven't freaking
liked and subscribed by now. And told your mother.
And told your dog and told your boyfriend or girlfriend or
whatever, just go do it. Help us out.

(01:09:49):
Come on. Another episode where we waited
till the very last second to throw that out there.
Also, next week is going to be episode 50, so we're thinking
about doing a live stream for that.
Come join us and come hang out and we'll catch you guys in the
next one. See ya.
Later.