Veo 3 Makes Yesterday’s Best Look Like a Beta Test + Runway & Midjourney Check-In

Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
(00:00):
What's up everybody? Mid Journey Fast Hours podcast
episode 4040. Whoa, yeah, whoa.
Yeah, wild, right? I don't.
Even remember when we started this?
Was it? Was it June or July of last?
Year, man, I want to say it was like, right?
I think it was like that first week of July.

(00:20):
All right, so right after July 4th.
It feels like we've been doing this longer.
Yeah, it's crazy. It hasn't even been a year.
I mean, considering like all thethings that we've gone into, I
mean 40 episodes of diving into primarily mid year hours.
Of stuff. You know, but but like really
getting in, I think to like at awhole like this, just like
creative process when it comes to AI and the capabilities, the

(00:44):
use cases, the strengths, the weaknesses, the road map, you
know, the promise. I mean, so it's just like it,
it's been crazy that all that's happened in less than a year.
And I think we're in this just like crazy compound effect with
with AI speed right now. And I think it's only going to
get crazier in the next few years.

(01:05):
So wild times do talk. About and we always have stuff
to talk about. That's what's crazy is that this
we could do this once a week andwe probably don't even have
enough time to talk about all the developments that happened,
which is, you know, also for anyone that's been here since
episode 1, shout out. You guys are hell yeah, thank
you. Hell yeah.
Come a long way since episode 1.I'm scared to go back and and

(01:27):
revisit episode 1 now. Oh man, that's a you know, it
wasn't. I listened to it maybe like a
couple months ago. I was like, it wasn't as bad as.
I thought it. Yeah, I remember too.
It wasn't as bad, but no, but it's still definitely like we,
we've got more of the structure down, you know, we still have to
work on some of the things like like our interview skills and
like figuring out how to make that a little bit smoother.
But hey, guys, we're trying, youknow, Hey.

(01:49):
Man, it's it's like this is thisis our favorite part of the
week. You know, Rory and I, and it
feels like you and I have only gotten more and more busy.
So I think the fact that we get to catch up and and have this
sort of like nerd out session isis awesome.
But you know, I think today, right, like last time we
covered, you know, Omni ref Exp parameter, we went really deep.

(02:13):
We did a lot of experimentation.We showed you guys a lot of
visuals. If you haven't seen that
episode, highly, highly recommended.
It was probably one of the better ones we've done with
visually showcasing kind of the different observations and
capabilities that exist with those things.
For this particular episode, we were talking just about video.
How could we not, right? Like video at large across AI,

(02:35):
right? Of course mid journeys got a
part of this that's coming. We haven't seen anything yet.
There is an update there that will run through.
But at large, I mean the pace and velocity that we're seeing
with update, update, update and then we I feel like we got this
just in crazy level up milestonemoment that we just saw with

(02:58):
VO3. Totally big time was and if
everyone you know, you've been following us for a while, we've
been a little bit behind on getting episodes out.
So that's an apology basically from me because I've been gone
for the most a month so between between both, you know,
conferences and other things that are going on.

(03:18):
But it's like we're back. We're back now probably for the
summer and we're going to be continuing to do this.
But the I was away and I was like, I got rumblings that
Google was going to drop this whole new creative Suite.
And I was like, oh God, please don't do it while I'm away.
And you know, luckily it happened on Tuesday and Google
just again pumping out great stuff.

(03:39):
Now, that being said, with this new release of what they're
calling Flow essentially like a creative suite, right, where you
have access to all their new tools in one place.
So you can use VO3, which is thenew video model.
You have Gemini 2.5, which is, you know, available within.
It's actually with, I don't knowif it's with Inflow, but there's

(04:01):
Imogen 4. Now they're updated image model.
So their whole goal is to generate, you know, a creative
workspace that you can do anything in.
And the real kicker and what thebig, big update was, is not just
the improved quality of the videos, but you can now add
dialogue and sound, which is just, again, things you don't

(04:22):
think you want and need until it's there.
And then you're like, I, I want that and I need that.
But then that causes a whole another set of issues, right?
So more variables introduced. Yeah.
And even like that from a consistency standpoint, like
getting a voice consistent from one video to the next, like now
that you have to control that, you know, it comes a little

(04:43):
harder. So it's just again, I still
you're starting to see, I think we're going to have a
consolidation moment sooner or later.
You're starting to see like Google was behind, right?
Look, it felt like they were behind last year, and now
they're just like pushing ahead.It kind of felt like, Google,

(05:03):
what are you actually doing lastyear?
Like they were so quiet for a long time to the point where you
kind of felt like it. Google, I know all this money's
coming in, but are you, what's going on over there?
Are you guys dying? What's the deal?
Yeah, 'cause I mean, they had all the, the SERP, you know, the
obviously like the SERP disruption with, with LLMS

(05:23):
coming into play, right? Like the way people search and
get results for things. I mean, yeah, dude, it's, it's
wild. Their their pace right now is is
really picking up. And like, this is where I don't
know, and I'm being candid aboutthis, like who can keep up with
them maybe outside of like the Meta realm or the TikTok realm,

(05:46):
because it's just about data. Who has the most data Google
has? You know, basically every image
that's listed on Google is categorized into, you know, it's
going to be probably filtered into their image data process.
I'm guessing they're doing the same thing with YouTube.
So YouTube gets while like 30-4 years of content uploaded every
day. So again, you know, if you're

(06:06):
not familiar and you're on YouTube and you have videos, I
think there's a space you can gooff to check.
You know, like I don't want to be part of video training, but I
don't know if anyone, how many people are doing that.
Where is that at exactly? It's somewhere in there.
Somewhere buried. That's you know, our videos are
probably in there for the talking head videos that you can
now create. With VO3.
But I just don't know who else has that data set other than

(06:27):
someone like meta or. Well, I think, I think that was
interesting 'cause I, I, you alluded to that, I think before
we really even saw VO2 come out,like I remember you talking
about this idea, right? Of like who, who's got more
training data than Google, right, 'cause you've got all the
stuff from Google itself, the platform search engine images,

(06:52):
things like that. Then you've also got YouTube as
a whole. I mean, it's been, and those
are, those are just the bigger pieces of the puzzle.
Not, not any sort of like fragmented products or companies
that they've acquired or bought or integrated along the way.
I mean, so yeah, I thought when you called that out, it was, it
was interesting. And I and I was nodding my head
like, yeah, that's totally true.I could totally see that.

(07:13):
And now it's really come to fruition here.
Because you have to think about where mid journey has to source
images from, right? Like it's not native on their
platform like Google's sort likebasically sourcing stuff
natively from their platform. Again, ChatGPT probably going to
be able to do this just based onthe scale and size of who they
are. I don't know what happened to
Microsoft. I guess they just like

(07:35):
disappeared and like, haven't done anything in this game.
You know, you're thinking about the text, the big players in the
tech space and what, you know, they're able to do.
But Google, yeah, this feels like perfect for them.
Now, I will say I do have a gripe with Google because they
seem to have like 1,000,000 products and they're all in
different places. And if they all have different
names and something like ChatGPTbecomes so much easier because

(07:57):
it's like, oh, I can do everything in one window.
I know where it is. 100% right like.
That's my 1 gripe with Google isthat there's just so much I
don't. Even yeah, product overload and,
and the naming and all that. That's that's such AII notice
that all the time as a marketer too.
It's funny that you bring that up because you'll even see that

(08:17):
in in smaller SAS companies thathave more than, let's just call
it 2 products, right? It's like after the product that
they're known for, right? Like you're going to name seven
other new products. It's almost like are, are, are
these just maybe features or canthey be a part of this naming
convention for the one product essentially, right.

(08:40):
And so there's this like chickenand egg problem of is this the
company or is this the product suite?
Should it just be named with thelike, because no one else is
going to remember every single one of your product names except
for the people in your company or maybe the maybe the actual
buyer, you know, at the finish line, the decision maker who's
purchasing, right? Other than that, you've got an

(09:01):
uphill battle trying to promote 234567 thousands of different
products and people expected to remember those names and recall
what they do. Yeah, good luck.
That's what it's like you go into Google and it's like, where
do you generate images? Well, there's Imogen 4 that you
can go utilize. There's there's Gemini 2.5 now
and then there's Whisk. And it's like, why are all

(09:22):
three? It's like the opposite problem
of mid journey where they have so much in one platform and then
Google is separating each one ofthese.
So it becomes what? Like I think they could
integrate Whisk into Imogen and then just it makes it a little
bit easier. I just don't know why.
And if people aren't familiar with whisk, it's basically like
like an ingredients sort of builder.

(09:44):
Like you, you put in a characteror a style or whatever and you
blend everything together, right?
You can also do that in Gemini just by pasting a couple images
in there and saying like blend this stuff.
But it's it's really just. Are they calling this the AI?
Like if that is the case, it's like just call it that.
Yeah, because then there's AI Studio, but then there's also

(10:06):
Flow, which is flow is where allthis, you know, the VO3 stuff
takes place. And then and then and it's like,
OK, is that part of this right? Like again, it's very confusing
to your point. It's but they just they need to
like they're so good at product dev, but then like making it
easy for everyone and then I don't know if I don't know if I

(10:28):
have it for personal or for business.
I like this one. This one's a pain in the ass is
I I signed up for flow with the wrong account.
I wanted it for my business account, but I was like logged.
You know how when you logged in as a certain profile and it was
my personal Gmail and I'm like, I don't need it for that.
I want the extra space and. I have to go.
Figure out how to switch my account to whatever because I

(10:51):
paid just so everyone's aware, Ipaid this stupid $124.00 a month
because I had to see what was going on here.
And you know, granted, the otherthing we should say about the
VO3 and flow is that it's expensive as hell and you don't
get that much. So like I think it's 83

(11:11):
generations, you'll run out of your monthly credits.
So you got to use it judiciouslyin terms of like we like I'm
only using this for when I'm dialed.
It's not a playground like mid journey is where you can go and
just like. Yeah, you wouldn't.
You're not starting from zero here.
You're you're probably have already got a few of these raw
materials or ideas conceptualized in some way.

(11:34):
Yeah. What do you, have you seen what
happens after you run out? Can you top up?
Can you like what is that cost? There's additional credits.
Let me actually let me see if I can pull it up so I can show
everyone the pricing here, just so we're all transparent about
it. Well, I think you're it is.
They've got a deal right now cuzI was just looking at you
yesterday. It's like 125 for the first

(11:55):
three months or something like that.
Yes. And then it's I think.
Double. I think it's yeah.
I was gonna say, I think it's double that.
Yeah, after. It is cuz then I'll go into my
where I'm almost out of credits.What's?
The it's a big, it's a big expense item, I mean. 100.
Percent because because when you're thinking about this,
unless your company or agency ispaying for it, if you're a solo

(12:18):
person, this is probably one of the more expensive piece of this
is probably your most expensive subscription you've got.
Yeah, and they did, you know, they were, they were nice and
they threw in, they threw in YouTube Premium for everyone.
You're $6 a month there or $12.00 a month, whatever it is.
But here's the here is the in the inner workings of it.

(12:42):
So, you know, the one thing thatI found is that you can, you
know, you see how many credits you have.
I started with like 13,000 and I'm down to just basically the
end. Already so So what is a what is
an average run credit wise take?Do you think I.
Believe it's 150. Per generation and I think it's
like 1212 five in terms of like 12,500 credits, I think you get

(13:06):
with that if I remember correctly.
Yeah. So you have the options for the
three models here. My, if anyone is going to use
this and wants to play with it, my best suggestion is to start
with either VO2 quality or fat like their quality model.
Sorry, the quality model, which is it's a slower, higher quality
model, but it's, it's so much cheaper in regards to credit

(13:28):
usage. And then like figure out if the
aesthetic or prompt works 1st and then bring it into.
Great call, right? Yeah.
But just to save some, just to save some credits, because you
can burn through this, but also you can add credits.
How? Have you made any quick
observations on the coherence with two versus 3?

(13:50):
I mean, like, I'm guessing it's,it's probably not that different
than in that sense. It's it's definitely better.
Or it does feel different I guess is my question.
Yeah, it's a little, little less.
Let's do it this way because there's there's so many
additional features you you kindof miss on some of the stuff

(14:11):
that VO2 did, which was like more extreme motion and does it
very well. But with that being said, like
the quality is better, like the quality of the output is better.
Like this one. You see, you can see my screen
on Twitter here. Yep.
All right, so like this one, this prompt, you know, low angle
selfie footage of a fat man running and laughing

(14:33):
simultaneously like nails that his laugh mixed with gasper air.
I don't know if I can play this.If anyone can hear it.
Can you hear this? No, because I think you got the
the Airpods in, so it's not going to give me the volume.
Fair enough. Regardless, it nails it nails
this laugh mixed with gasper air.
He has red hair, a mustache, a green sweatband.
So we get all that nestled next to his receding hairline.

(14:56):
So we have the receding hairlinewith his unkempt curly hair.
The camera shakes as he runs, you know, with vigilance and his
laughter makes the scene like, comical in life, right?
So this is a simple example. Nothing.
Like going here? Just it listens.
Right. It listens.
I mean, I mean, even with the image Gen. stuff that I played
with the past, the coherence wasfantastic.
I mean, you like it was really dialed in to the point where

(15:20):
it's like that's what I also canappreciate about mid journey in
that sense of like, I like that it has coherence, but it also we
we we've talked about this so many times, but leaves room for
that creative magic to take place.
Image Gen. feels like it's much more just precise coherence,
literal Co coherence. I think is is what I'm sort of
trying to say. 100% And then there's some, there's some

(15:41):
physics stuff, like I had this guy spraying carrots on a grill.
I haven't. Even seen these brother.
But you know, this is this stuffwas pretty.
I was impressed with some of that like that physics is pretty
good. This one I had a little I don't
know if you you're tuned into the side talk NYC for that go.

(16:01):
You know, it's just like these crazy videos in New York after
the Knicks play, just like you know, the Bing bong.
I don't know if you've ever seenthat, but they just think
interview on the street. They say people say it's crazy
stuff in the crowd just erupts into chaos.
It's. I'll share the account with you
after if anyone's interested. Yeah, there you go.
But like this one, I was impressed with, you know, like
the camera motion, the way that he opens.

(16:22):
Up, yeah. Right.
Like just the way that it follows him, the way that you
know, typically that would be really hard shot for this to
produce. You know, something like this
with all the stuff going on in the foreground, being able to
preserve the mid ground detail, you know, the way that the water
is moving from a physics standpoint, the way the truck is
bouncing. Yeah, it's, it's, it's like,
it's like almost like right. With a lot of these video miles,

(16:45):
at first you, you, you would getlike one or two variables that
would kind of like give it a little bit of a realism sparkle.
You could see it, but it like it, it lacked punch because
there were other variables that were either static or not
rendering correctly. Whereas this is like really
stacking on variables, right? Like the the camera shifting,

(17:09):
bouncing, the tusks going up anddown the proportion of the leg,
like the legs are the walk is clean, right?
Which for a long time is such a problem.
And you've got the person on top, right?
Bouncing around, the feathers bouncing like they're just so
many different things that have to be on.
Tears sink there. Yeah.
Like the the the trunk moving. The splashes every Yeah.

(17:31):
It's impressive, man. Like this one again to the same
thing, you know, to the prompt coherence.
I was really impressed right like just you know, camera
pushes in on a man sitting at a New York City diner table at
midnight. Midnight might not be
appropriate there, but his arms are folded.
His head is down resting on his arms.
Suddenly a hand holding a plate filled with a Patty melt and a
massive portion of fries, you know, enters the scene and

(17:52):
slides the plate on the table infront of me.
Raises head to show an extremelytired little bags under his
bloodshot eyes. Long night of partying right
like this. It's just listening to
everything I'm doing. I'm saying like, and it doesn't
the thing here that I that I'm liking because I don't have to
go so deep into aesthetic to getthis look, you know what I mean?
I have to do like 35mm soft blurin the background, like, you

(18:14):
know, the contrasting colors, like the leading lines with this
stuff, like I don't have to describe all that.
It's so I'm saying. Man, I think we, I think we went
through a real OG era of analog like AI, right?
With the level of context and things that we had to, you know,

(18:36):
really apply there, especially after that first wave.
And I'm thinking like with this in terms of mid journey,
remember, like, you know, when you got early on with, I don't
know, V3 or whatever V4, like you probably weren't getting
exactly what you wanted precisely anyway.
So it was a lot more of like, let me throw in these creative

(18:58):
tokens and, you know, buckets tokind of get something unique
that has a loose interpretation of what I've got.
And then it went to right when it got to like 5, you know, it
was us really dialing in these. OK, think about this from like a
maybe even a photographer's standpoint of realism.
If you're going to go for that, right, you need to be thinking

(19:19):
about camera angles, maybe even throwing in a camera and lens
and aperture if you want, you know, shutter speeds an option,
lighting shadows, you know, textures, right, like all that.
And now right like that languageis sort of like coming back to
the state of it gets it, it getsit.

(19:39):
And right, like there are a couple different ways to
leverage that, right? Like you could still throw some
of these things into a GPT if you need some help crafting
prompts and stuff like that. But the point is, is I think
like the the analog era of kind of like tapping into each thing
and really having to think hard and deeply about and revisit
notes and things that you it's probably over, right?
Yeah. And that's, that's what's

(20:00):
interesting here, right, is there's there's so much, so much
variation in between each platform and what's utilized.
Like I have a totally different way of prompting VO2 or VO3 than
I have prompting Cling 2.0, right?
Like it's so I know how Cling works.
Cling has been fairly consistentfrom model to model in terms of
what works and what doesn't. You know, it feels like, you

(20:21):
know, mid journeys switched withtheir models in terms of what
works, what doesn't. Like each, you know, each new
version, you kind of need to prompt it a little bit
differently. So yeah, you know, for Cling,
I'll give them their, I'll give them their roses on that.
It's been seamless sort of transition each one of them.
And I really like it for that. Now, the other thing to note
here, which is cool because I was able to this was something I

(20:44):
was trying to do for a really long time was these like longer
one shot takes where you just have like one single character
and you're following them for, you know, 4050 seconds.
I've been trying to do this for a while without having like the
the sort of image or like the the scene breaks where it's sort

(21:07):
of like stops and then jumps again, you know, without having
to do a ton of editing. So something like this.
I was like really impressed withthat.
I was able to just take that first shot and then extend and
then I have them walking through, you know, an entire
environment here. It goes from a party to a
dressing room, you know, then tobackstage and then he'll
eventually come out on stage in front of the audience.

(21:28):
But being able to do this now you can do this is the this is
again The X Factor. I think here outside of like the
quality and the sound is that you can now do this within like
a they have a scene. They have what's called a scene
builder. So when you're in here, let's
just say I like this. You can go add to scene and then
you get a timeline. And then you can from here, you

(21:52):
can click and go extend. So I can just extend this clip
and keep it going, right? And you just when you hit
extend, it's just like you type your prompt and extend the clip
as. Long as how's the, how's the OR
how's the consistency quality ofthat?
It's it's good as of right now though I want to make sure that.
I'm are you having to prompt on top of it in addition to extend

(22:14):
to get a little bit better results or kind of let it drive?
No, I've been I've been prompting to sort of get better
results, but as of yesterday andI don't know because I haven't
run this again, but you could only extend with VO2.
So let me see if I just. Run this.
Interesting. This shot continues.

(22:34):
I'm just. Gonna does that affect quality
in any way? VO3 to VO2.
Right here. So switching switching you to a
compatible model for this feature.
So you can't extend. So this is where the downfall is
like this first video that I didhad sound right?
So now when I extend, it turns into VO2.
So I'll have to use VO2 to continue to extend it, right?

(22:57):
Which is either fast or quality and you'll get a drop off in the
quality of the video and you won't get any more sound.
OK. So you would so you do notice
the quality drop off? Correct.
Yes, that's it's, it's definitely fuzzier.
It's less sharp, you know, the colors are a little bit more.
I found VO always has like this wants to be blue.

(23:20):
Just yeah. Yeah, it wants blue.
Hey, hey, Rory, what about lengths of these videos right
now for VO3, right. So, OK, you've got you've
generated a clip. It's got sound, you know, you
know, you probably at this point, I mean, unless you had
to, right? Don't want to take it out of
another? Take it into another tool to
like, you know, manually add sound and manipulate it.

(23:43):
It doesn't make a lot of sense right now.
How long are these clips? So they're 8 seconds each, but
you can then jump to can also just generate a new scene in
VO3. So you could also do that.
You don't have to have, you don't have to use this 1st
frame, right? We can use high quality here and
you could just generate like a totally different clip, but
you'd have to text prompt it to make it look considerable.

(24:06):
So that's the other thing to know is that when I go to.
So no kind of like style reference for color matching or
aesthetic in that regard or. No.
So the other thing here is when you go to when you have your
drop down, you have text to video which is basically is VO3

(24:26):
at the moment. Right now it sounds like you can
do the apparently as of as of like 10 minutes ago, I just saw
on on my WhatsApp that you can now do image to video.
So you have 1st frame, last frame.
Does the image does Google allowyou to take outside images or
does it have to be Google generated?
Let's see. I don't know if it.

(24:46):
That's what I'm curious about. I don't even know what this
image is, but we'll see. All right, cool, let's see crop
and save. OK.
Let's see if we can do it. Yesterday it wasn't allowing
that, so so it is. OK, which is awesome.
So you could take third party images in here for that frame to

(25:11):
video. You can also add an end frame
here. The other thing that's nice is
that we have camera control. So you can just, you know,
basically you don't have to describe this in the prompt.
You have all of your, you know, basic camera controls here as
well. Now the interesting piece is
this gets a little bit gets a little bit deeper.
You can go ingredients to video,so similar to Cling's

(25:34):
ingredients where I could add, you know that.
Object scenes kind of thing. Different people or different
objects, right? I don't know what the what the
filters are in terms of like I could add this guy right So I
can have a consistent character.How?
How does it? How does it know whether to do

(25:56):
you have to explicitly call out that you want that guy versus it
maybe interpreting that scene asan ingredient?
Does that make sense? Like.
I haven't tried it yet because yesterday it wasn't available
with VO3 and I'm just like, I know how VO2 works.
Like yeah, it does. It does work.
It does place the character intothe scene fairly well.
So the other thing too to know is like when you're in here, you

(26:21):
have the ingredients, then you also have candies, ingredients
of a styles like that. OK, got it.
So there's also if you're doing,you want to add an ingredient,
right? It'll give you these options,
generate image upload or use something that's previously
utilized. You can also generate and then
you can go use image N 4 to get this, you know, like just

(26:43):
character, 1980s movie characteror like 1980s movie character,
right? Like you can just generate here
and then use this as a frame. So you can use Imogen straight
in here. It's generate frames as well,
which I found to be useful. Imogen 4 like I'm not overly

(27:04):
sold on it. I thought 3 was really good.
I think there's some still has alook to it now.
Yeah, but you know, like this guy could totally use that and
just start from there, right? And anything you want to do with
these people and you just basically add this as the frame,
you use this image and then there's your frame and you can
start from there, right? So that's one way to use frames.

(27:26):
The other way is if you want to go into this video, right?
Let's just remove this from scene.
Oops, let's add the scene. You can be like, all right, I
like, I want to start my next video from here or I want to
extract like a frame like this. Like maybe I want to extract
this frame yeah and just hit save frame as asset.

(27:48):
Sick love that. Yeah, which is super nice.
That's a man. That's such an underrated thing,
right? Because how long have we been
dealing with the fact that if you want a certain frame of any
video that you basically just have to screen like pause it and
screenshot it, you know, and then probably lose a little bit
of quality in the process? Yeah, cuz you can you can also

(28:08):
drag like you can drag to sort of like yeah, love that
timeline. Like I said, you can once you
start to add things here, you can arrange like I can flip the
scene and put something you know, in front or behind or get
rid of it if I want to. And then the other good thing is
you can basically edit within here or you can export within
here. So once once you have like a, if

(28:29):
I go to another one where I might have like a full scene
built, let me see if I have one here.
That's that's relatively. I don't know if I have one in
here with multiple that I started, but it's all right.
Let's see. No, yes, no.

(28:50):
OK, Regardless, you can downloadthe entire thing.
So you can just like once you Add all these scenes in here,
right, you can go and just hit download.
It'll download your entire clip.So you have that functionality
as well, which is great to have.You know the fully edited thing
in here and again, you can trim it up and basically edit it how

(29:12):
you want. The other thing that I shall
mention last, there's that the one native feature that is great
is when you hit download, you have the ability to turn into a
GIF original 720 or you can upscale it to 1080.
So you have that ability in here.
Upscale cost you additional credits or no?

(29:33):
I did it once and I honestly don't know if it cost me extra
credits or not. It wasn't like an obvious thing
like where. It didn't say.
It like it doesn't say it now, which I know like runway will,
right. Like on the video it's like
upscale of 4K. It'll tell you how many credits
it'll cost. Yeah.
So there's just a lot of, there's a lot of stuff going on
here. You can see how this is sort of
like they're trying to take thatSora model now they don't have

(29:57):
the things like Sora has like remix and blend and you know,
the timeline features in terms of little bit extra additional
things, but Sora's way less coherent than video is.
So I'm just like I said, I'm just impressed with this as a as
a concept for being able to stayin tool here and not have to

(30:19):
jump back and forth a million times.
So, you know, that's that's where I'm seeing the best, the
best sort of it's best word point.
That's sort of like concepting for a tool.
Yet from a video standpoint, that's me though.
And I think runway does a great job.
I think Cling does a great job, but they're also, you know,

(30:41):
we're at the back end of this. I say this all the time like.
The back end, yeah. Because we've been with Mid
Journey or Runway or Cling for along time now.
They just keep adding more features.
And then it's like, alright, there's all this stuff.
Yeah. And then like a new one comes
out and it's so clean like this because they haven't had all

(31:02):
that. And you kind of appreciate it.
Yeah, I, I know, dude, totally. I, I think it's the ADHHD and,
and us and and the wider population because it's yeah, I,
I've always felt that way. It's like there's something
magical about less sometimes, right?
Because it's easier to figure itout.

(31:23):
You can connect the dots. It doesn't feel overwhelming.
I mean, I love mid journey. The fact that there's still so
many things though that I eitherforget about or haven't used in
so long just purely because I forgot about it.
I mean, it's, it's mind blowing,right?
Like it's hard. Use all of it.
You know what Canva used to be so simple and easy?

(31:43):
I don't. I don't even know 1000.
Things to do in there. Bro, I don't even know what
canvas doing now. I mean, like I I mean from a
business standpoint, it's it's great.
Yeah, from a user standpoint, I agree.
Right. Like that was the that was the
tool we got, you know, early on for non designers, right?
Or you know, lo fi stuff or being scrappy small teams.

(32:07):
You don't have a designer, you don't have budget, right.
Canvas yeah, dude, you're totally right.
Like and there was something special about that.
Now I I can't even came and fathom everything that you could
do in there. Now I've spent some time in
there recently, like in the lastyear or two, but not not taking
advantage of or not really paying attention to like all

(32:28):
this new AI stuff that they like.
I don't really. I'm not going there for that,
right? Yeah, because I used to use it
as you know what, I didn't want to use Photoshop or something
complex and I didn't want to like have to before Photoshop
allowed you just just point and click on a layer.
You used to have to go select the layer, then move it, then
select the other layer, then move it, which was annoying.
So go to Canva and just like be able to move everything in one
canvas quickly for things that didn't need like all the

(32:51):
firepower of Photoshop, right? So I, I don't know where, you
know, they've added so many things.
And a lot of times people will tell me, Oh yeah, Canva can do
that. I'm like, what?
I missed that. Up there and even if they can,
it's almost to the point right where we've talked about this.
It's like the adoption. It's like am I do I see myself
actually changing my habit to then now start using Canva for A

(33:14):
or B or an AB and C now like just because it can?
Probably not. You know, yeah, there's a, it's,
it's unfortunate, a lot of theseolder tools that sort of like
got me through life, like work life.
Yeah, man. Say afterthought.
Photoshop is really becoming an afterthought now, and like

(33:34):
Figma, I don't even know if you saw what Figma dropped recently,
but I've just. Been hearing that they're
dropping more and more, you know, and I can't keep up.
I can't keep up but. They basically integrated like
cursor into figma. So you can, you can do like web
design and coding and development in there.
Like I, they have a new website like an AI website builder.

(33:54):
Like I can just go build a website simply within Figma
instead of having to utilize oneof these template builds.
Like if if you're not a seasonedweb designer, right, or someone
who understands coding, web design kind of sucks because
you're just at the behest of like what the template can do.
And that's it. And now you can go in there and
customize it the way you want. It also has, you know.
Or just like a, or just like a developer on your team, like

(34:16):
maybe there's just one or two people like, yeah, that's
happening where it's just like, I'm glad we had that.
But that feels like a, a big bottleneck here for us.
Like that. It's not this democratized thing
that more and more people can act on, because now, now you're
relying on somebody else to go in and make changes to every new
web page you want to add or build or wireframe you want to

(34:37):
reconstruct and this and that and the other.
And that's just not a scalable thing.
Let me, let me actually, I'll just pull it up real quick so
everyone can see. Yes, I know we're off a little
bit, but I know there's definitely people here that are
using Figma. Like I was just playing around
the other day. I was like, all right, I just
pulled in a bunch of different things and if I wanted, you
know, a different footer or something and just go and

(35:00):
basically add and then, you know, navigation, they have
different heroes or features that you can add like, oh, let's
just add this bang. You know, that just adds it
immediately. So you have the web design here
and then it gives you the mobiledesign right next to it, which I
like. If you want to add a page, you
just go there and you can design, you know, each one of
these is interactive and responsive.
So I'm like, this is great. I can just build landing pages

(35:22):
on here all day. Don't have to go to, you know,
don't have to go and like use these template builders.
On. Website things like.
That I might need a little. I might need a little demo on
that. Rory Flynn.
Dude I was really liking it cuz there's the other one was was it
buzz that I was using? I don't remember if it was Buzz,
which is you can just make assets, right?

(35:44):
Like you can just make. It's like this is their new
version of Canva with AI baked in.
Yeah. Generate templates and things
like that. That feels that feels long
overdue for. Them yeah, super easy.
The other thing they added was this make.
Let's see if they have if I haveit in the make do.
You see Framer and Figma kinda that's it in joining here, like

(36:06):
in terms of like, they're comingcloser and closer together.
I just typed give me a sneaker ad and then it dropped this
which is basically like, I wouldn't say it's an ad but it's
like a card for a website. Yeah, hell yeah.
Like card that's. That's great.
I mean the UX UI is like. Yeah, perfect.
Perfect, you know, even then gives you the additional format,

(36:26):
right. So I was like, this is cool, you
know, and I was like what's you can just type in here and it's
run through Claude Sonnet. So it's you can code really
well. It's basically like using an
MCP. You can also, you know, drop in,
you can attach a design to sort of give it guidance.
You can attach an image, which is essentially framer just be
like, here's a website that I like, put it in like design this

(36:48):
for me. This can also work on a few
different things. So I'm loving where all this
stuff is going right now. It's just becoming, it's
becoming a playground and I feelbad for people who are just
starting because there's so muchto do to learn and do, but you
know, they keep making these developments and it's the one
after the next. You, you need, you need internal

(37:13):
adopters that are just curious by nature in the company and you
need multiple people at the moment, right?
Because most companies are not going to spend at the level that
they would need to to upskill their own employees, which is a
whole separate other conversation.

(37:33):
But also to your point, these things are changing so fast.
So you could hypothetically, right, bring in a trainer or
this or that and the other. And that's good in that moment,
right? There's a lot of value there.
There will be things that will be Evergreen for a while, but
there also be things that'll really perish quickly, right?
Because it's changed. The whole thing's changed,
right? Like even just a couple weeks

(37:54):
ago, right? It's like, you know, hedgerow is
like kind of like this cool little thing that you could
probably, you know, start to adapt in like with VO3, you're
like that. I don't know, you know, I don't
even, I don't even know anymore,Right.
So I mean like, yeah, like I like for example, I'm just
thinking of a client I have right now.
They're doing a they're doing a presentation with with basically

(38:18):
like AI generated people that will serve as like an agentic
part of their software. They're going to present at
their conference. They're putting it up on the
screen. They want to show motion, they
want to show them talking and, you know, making movements and
that sort of thing. It's like, OK, like they're
already playing around with Hedra, right?
And then you got Theo 3 drops, right, Just like, well, if you
guys are probably trying to do like full body motion and you

(38:40):
know, like get them in scenes and you know, like there's a
pivot, right? So like you're trying to do a
project like that really truly while the car is moving, you
know, trying to paint the car while the car's moving or
whatever that analogy, this. Is why it's tough man.
Like as I, I've people have sortof, I've been approached by a
number of people for longer termprojects, like bigger projects.

(39:02):
And I'm just like, if you're working on something for more
than a month or two, like basically your first month or
two of work is just, it's just scrapped because you're doing it
with tools that are outdated by that point.
So you know, it, it just doesn'tmake sense.
Like it's, it's, it's hard. You have to be able to do things
quickly. Like if you can do, if you can
utilize the tools and get to an end result quickly, then it's

(39:25):
fine. But if you're trying to.
Do like AI think that's a great.Film.
Right. That's what I'm saying.
Like this. You.
You. Yeah.
What are you going to do? You're going to scrap halfway
through, you know? And so it's just this.
Yeah, I like. I don't think we've ever, I've
been at this point with technology ever like that, like
you, I can't, at least not off the top of my head.

(39:47):
I can't think of a situation like that.
Usually there's been these long gaps of time.
Yeah, yeah. And we couldn't do like a
podcast on Apple, you know, whatare we going to get every year,
you know, the iPhone, you know, get the the launch of the new
iPhone colors and like in the operating system and like that's
it, you know, so it's it's this stuff.
It's just such a little micro developments at all time.

(40:07):
And then you get. You know, use something like
cursor or lovable or framer becomes big in the zeitgeist and
then figma's like zeitgeist. I'm just going to pull it in.
You're back on your you're back on your zeitgeist bullshit.
It's very it didn't. It didn't feel, it didn't feel
like the right word until recently.
Where? I love it, dude.
Yeah. All anyone talks.
About I know, I know, I know. I'm just giving you I got to

(40:29):
give you shit because you'll you'll pull out like a Beck in,
you know, like something every episode, but then you'll come
back with something that like a zeitgeist.
So. My brain just firing on early
morning caffeine. We're a little earlier.
Hey baby, we are so. That's true.
That's true. SAT words are flowing.
Yeah, now. But this is the other thing that
was interesting recently was again and had this conversation

(40:51):
with a few people is just runway, right?
Like Runway is really creating alot of useful features and I I
think you know, some of it gets overshadowed by what's going on
with VO. It's such a cheaper model to
utilize the quality. You might sacrifice a little bit
in the initial output, but theirreferences feature is excellent
and I. Agreed.
Really. Well, dude, I'm so glad you

(41:13):
brought that up because I, I think that's something we're
talking about too, right? It's that that exact point of
what you just mentioned of the use cases now, like they've
built in different things that maybe aren't so obvious, but
you're like, you're following other people that are using a
reference and they've unlocked like a way that you probably
didn't think of initially for this, right?

(41:34):
And you're like, oh shit, I didn't even think about it like
that. Whereas before it was a little
bit more cut and dry, you know, with with kind of you knew what
you could use it for in the application.
But you're right, like there's now sort of like some of these
Gray areas where creatively it'snow opened up.
There are some different possibilities and use cases
available with that, with that references, part of it, with the

(41:57):
style transfer part of it, with some of those other things they
just rolled out. Yeah, this is great.
I mean, there was I saw, I saw Crystal ball, their founder put
up like a really good image of just someone that put like a
basic framework of a structure in there.
It was like car here, person here, this here and it just it
listens. And I was like, that's awesome.
I try, I tested that. It worked very well.

(42:18):
Just, you know, again giving it loose direction.
I'll I'll try to pull this one up.
Yeah, it was, it was, it was kind of like that feel of, you
know, kind of what we were getting with with ChatGPT, you
know, with the sketches or like that wire framing sort of vibe
to it, right. Yeah, so it was essentially
like, you know, it was like the full sort of representation of

(42:40):
it, but it was just like, OK, man front for you, standing arms
on child, child front of you, sitting on stool, you know,
drawing the stool, checkered floor pattern, woman side of
you, standing, body facing left,head facing right.
So, you know, it's giving you all of this, what's what I want,
even the checkered floor sittingon the stool, like the body
position when you look at it, it's all pretty much accurate.

(43:01):
And using these two, you know, using this as a reference image,
these two people and the child. So that that to me, I was like,
all right, like we can, we can do stuff.
And like even then everything from the pattern on the scarf
here, I'd say that's, that's pretty well transferred.
Even, you know, the the jacket, the color of the shirt, that
stuff matches our look. The sunglasses match his look.

(43:23):
The sunglasses match didn't put the hat on him.
Regardless, I'm not going to complain about that too much.
Probably could have just rerun it and got it the same.
But you know, to me it's impressive.
Like this is a this is a really good translation from this, you
know, from this to this, right? Like that's that's as close to
an AI character consistency as you're going to get.

(43:44):
So I, again, just really like what they've been doing and
giving them their flowers in that sense, because we just
wanted consistent characters forthe longest time.
That's it. Yeah, now it's all now it's all
sort of. I was just going to poke in on
this a little bit because pulling up crystal ball's, you
know, X account here. So I just saw this one can

(44:08):
runway fold laundry? Seems like it can.
Wow. OK so so we put shirts, 5 shirts
pointed out the color and the item.
Sort this and remove the basket from the shot.
Let me not get lost to my browser here and.
That's a good one. Not bad.
Five shirts, brown pants. Sick.

(44:29):
Got it. Sick.
Let me go back because there wasa bunch of really good examples
here. Here's sort of where we were
talking about like the sketching, right?
So blocking scenes, boom, boom, show me the man from image 2
frame through the windshield of a car.
Like the reference in one, you know, like this is this is kind
of what we're, you know, alluding to, man.

(44:52):
Maybe maybe like really toward the beginning of this podcast
was like just the way that you prompt for these things.
They're just so many ways to prompt, right?
Like initially it was just this imagine you've got an empty box.
Yeah. Now it's like, you know, you
could do stuff like this, you know, and it's like you don't
have to this, this is almost like a different muscle that
you're flexing right? Entirely when when you're

(45:13):
generating this, this kind of stuff.
Here's another interesting one, right where it's like, OK, take
your composition sketches, have the model turn them into real
images and video, you know? So you've got this, you've got
this, then you get the guy, thenyou get this scene.
I think the pioneer here was wascling with that.

(45:36):
Once I saw that, I'm like, oh, this is going to this is how
everyone's going to want to do it.
It's like hit this character, this environment, this object
like just mix it all together. I was going to say, was it, were
they the, were they the first ones that you saw that with?
Was that them like a clamber? Where it's, you know, outside of
mid journey where with like, youknow, style references.
Yeah, yeah, yeah. That way.
But yeah. There's there's so many good
ones in here. It's it's fairly, it's fairly.

(46:03):
I don't know if they integrated ChatGPT into the back end of
this. I was going to say, dude, that's
that's what I was going to say, right?
Because like it felt like that was you're seeing a lot of this
ChatGPT type of functionality. Our boy LR.
Yeah, our boy LR. So right.
Yep, here we go. Keep the car the same as image
one, make it driving the location for image 2.

(46:24):
Yeah, it's not a hard that's nota hard prompt to come up with.
All you're doing is taking two things.
You were blending them with control, right.
I thought was it. I think mid journey was the
first one to have a blend functionality in general, the
idea of a blend. Now this is like AI don't even
know that I would call this a blend.
Maybe like a smart precise blend, but like that's, that's

(46:45):
crazy. Like I want this.
This is what I've always wanted.Like layers and like, there you
go, ideas. This is this is the one where I
was like, this is genius. This is so easy.
Right. So you're just doing this.
Here we go. You've you're basically blocking
the composition, giving it a name.
Giving it the reference of the guy.
Boom boom. You know, awesome.

(47:08):
Like just really, really fun. Sick.
But this is it. I don't want to write paragraphs
anymore. No, sorry, no.
Not even. That's what I'm saying man.
And oh, we didn't even talk about this part, this try on
extension. Oh yeah.
Which I don't have it on my computer yet so let me see if I

(47:29):
can find do you have it on yours?
If not, I'll just kind of pull it up here, but I might have to
scroll back a little bit on thisbecause there's an actual, I
think there's an actual video that was pretty good.
I'll look for it for a second here.
If I can't find it, we'll just look at a static one.
But when that first dropped? Can you wait scroll back up for

(47:51):
a second just real quick and notto go off?
Which one? Keep going.
There was one with the green couch and a bunch of stuff.
That one just want. To see how that works.
OK, so here actually let me backout one second.
So using an interior mood board in a flat sketch.
Yeah. OK, so please generate an
interior image using the furniture styles, colors,

(48:12):
materials shown in one. So this this may be a little bit
harder to see for those of you watching.
So I'll just kind of like there are elements of this.
Let's just call it a living room, furniture, objects, decor.
Then the second image is the layout using shapes in that
wire. What are we calling this?

(48:33):
So wireframe composition? I I don't know what you want to
call that but. Whatever floor plan in this one
it's. Right, it's just like basic
blocks and and identifying thoseobjects.
OK, use these furniture positions, shapes and text
labels from the floor plan in two and then there's some
additional instruction around the wall paint color and the

(48:56):
flooring wood flooring as the base interior materials camera
perspective must must match the arrow direction indicated in
two. Oh, so they even threw and let
me see if there's an actual photo of that.
Here we go. OK, boom.
So he even. Yeah, smart. 3D, yeah.
You know, cuz you'll, you'll seethis also you used to see this a
lot with like lighting setups and photography and stuff where

(49:19):
they would just you know, if someone's trying to give you
like a tutorial on it or show showcase, it's like lights
coming from this side or this. This reminds me of that smart.
Like that though for lighting that might be a cool thing to
play with. Lighting too.
There you go. Yeah, that's that might be real
smart because sometimes there's there's trouble with I've always
had trouble with getting under light like life coming from
underneath. So in these image generators,

(49:40):
maybe I'm going to try that. I don't know if you've I have.
I've always had issues with. That would solve it.
I feel pretty confidently not even have tried that.
I feel like that would it workedpretty well given given if
you've got this capability that should work.
That should. Work.
Yeah, Let's see. Did it come?
Let's see that final picture, though.
Did it come? Out.
Yeah, I. Mean yeah, it placed everything
which is nuts. The window is in a different, so

(50:04):
you've got like window here. It's not perfect, but if you've
got some. Close enough.
Yeah, if. You've got some if you've got
some. Liberty.
Yeah. I mean, now we're nitpicking.
For sure for. Sure, you know now nitpicking
for what? Well, and it's it's impossible.
100% And it's also like worth reminding people of there's two

(50:29):
layers to this. There's the external ready for
business era and there's the external like we're showcasing
what's possible right now, but all of this is in motion.
Yeah, to then eventually be unlocked.
Yeah, right. So it's like we're also saying,
hey, look, this may not be a perfect today, but it's going to
be soon, right, Which is, which is also the exciting part.

(50:50):
But also take this stuff like these are all concepts.
You don't have to use them one to one.
Like they're all like, I took that car example and was like,
all right, let me try it with a family portrait And I was like,
OK, this works. So it's like it doesn't have to
be 1 to one. It only single use case using
that like we just did with that light direction or the the
camera direction. Like I thought of that
immediately. Let me try that with light,

(51:11):
right? Because that's like, what else?
How else can we take that sort of structure that people are
providing and like adapt it to our needs?
So it's just got to play around with some of this stuff and
runway is so much a. 100% you know, and also that is a, you
know, one other interesting thing about this, this is a 2D

(51:32):
thing, right? If you had this in 3D it would
be much more accurate. Totally 100.
Percent because this is basically saying, OK window, if
you're in a, this is a square room and the window is going to
be flushed straight ahead at, you know, 0° or whatever it is,
yeah, it's like, OK. But if you've got a a different

(51:54):
dimensional model I I would expect that to be much better.
Even no, but let me show you this real quick before just to
just to touch on that because wewere that's how I sort of was
thinking about it in terms of depth.
Yeah, so like with this one, youcan see sort of how it's layered
and stacked like where I want the person behind the child and
the. Woman behind the child, but
also. Sort of like how the floor

(52:15):
provides depth here like that's.Well, even though even even the
layering there is smart in the 2D 'cause I, I don't, I don't
know that I've seen a lot of layering yet.
Well, that was my you know, thatwas my intention.
Just so. That's good.
No, that's good, man. I'm calling that out.
I'm like, haven't seen that. But that's why that's why it's
like, oh, can it do that? That's always, that's kind of

(52:36):
always where it comes back to iscan it yes, cool.
Now let's push it further right,'cause you could do that room in
a similar fashion. You probably just draw like
little circles and be like, put this here, put this here.
You just need to get the dimension of the room right that
you're trying to to start with. So.
The the thing that we got lost in 'cause we were nerding out on
that was the Tryon thing. Yeah, I, I, I can't find a video

(53:00):
at the moment just on the fly, but that's incredible.
So it's the idea, right? Like you've got a picture of
yourself. There's a Chrome extension.
Again, I don't have it on my computer yet, but essentially
you can take an item and, and virtually try it on which I knew
that technology existed because I had a friend that was kind of
in that fashion space and told me about this maybe even like 2

(53:23):
years ago. He's like, dude, it's getting
crazy out here. So I'm surprised to see a
runway, you know, kind of like get into that.
It's incredible, awesome lead Gen. tool, you know, like to
utilize it that way. And then there's people like
What's Runway? I mean, dude, that adds a shit
ton of value right there. You're going into a whole

(53:45):
different space with something like that.
And that was Cling, like Cling did that a while back, but they
didn't go the extension route. So sometimes there's a benefit
to being second on some of this stuff. 100% yeah.
I mean, the the friction that takes place in trying to be the
first to come up with the idea, execute it versus oh, you have a
little bit of the playbook here.I mean, this is just goes

(54:09):
without saying, right? But just talking about the the
references for consistent building.
So you've got two things here, right?
He says all these images were, or what does he say, all the
images in the starter created just by combining the first two
images and asking Jen Ford to create different variations of
the subject in the location thatwe want, right?

(54:30):
So same girl, just different camera angles and different
focuses. Didn't do bad on the feet there.
Normally feed to me is worse than hands.
That's a you know what? That's a great point, man.
I can't even tell you the last feed I've generated.
Well, without shoes. Without shoes.
Without shoes, right feet typically to me have been so
much more gnarly than hands. Yeah, yeah, love the color in

(54:55):
this too. It's nailing that call.
I was waiting to see if that yellow would translate and it
did across. Across a few different images.
So there's again, there's runwaystuff it they, I think people
just get, you know, start to sleep on runway.
Candidly, the quality is not on a VO3 level or a clean 2 point O
level, but sometimes you don't need that, you know, sometimes

(55:16):
you just need something fun likethis and Runway can do that.
I think runway's great and. Same.
I mean, yeah, I think he summed it up perfectly.
It's got, it's got, it's got faults.
It's not perfect, but they're I think now kind of going back to
how we started this conversationwith Runway.
Now it's not so cut and dry in terms of the capabilities.

(55:38):
There's a lot more exploratory things and use cases that are
now available and some of which don't require all the variables
that maybe something like a VO3 would, even though VO 3 does
that stuff stuff really well. So they may have, at least for
the time being, both really gooddefined spaces within your
workflow and your tools, right? Yeah.

(56:00):
It's, I didn't see that. If you put that up there, is
that open available for API yet?I would love to sort of play
with that a little bit. More I don't know.
Certain spaces, new tools comingup that you can bring this stuff
into and use all of it, But there's, I'm finding myself more
intrigued by references than I am with let's say ChatGPT at

(56:23):
this point. ChatGPT, we think we have, I
think we've started to sort of unlock the faults.
I I think that's one of the, youknow, the image generator now
that within Sora and, and in chat windows, you seen those
videos of the people that are like, give me the same image
again and again and again. Yeah, I was telling you this.
Remember the rock example? Yeah.
Yeah, it's like that's pot. That's true, though.

(56:45):
It does. True.
It's true. I tried something, you know this
too, so I'm just calling that out for people listening.
But you do get better consistency.
If you're turning it into Jason code and you're saying, hey,
look, I want to I want to createmore versions of this.
And I mean this in the terms of like that could be that could be

(57:07):
your subject, that could be the style of the character and
whatever. And then really have it
breakdown like I'll maybe maybe this is worth sharing.
I don't want to go too too off with this, but here let's jump
in here and then let's go Where's this now I got to find

(57:33):
this that's. Going to be the hardest part.
I think it's under tummy ache relief.
Nice for my for my daughter. OK, so let me scroll.
This was actually part of a longer thing, but there was like
this really cool example and then I wanted to I saw I saw
this somewhere and I want to saywho posted this?

(58:00):
No it. Might have been OR oh, I saw him
do something. Similar it was I think it was
free pic. OK, I think it was free pic's
account. But like, you know, they, they,
they these were animations. So this is just like I took a
screenshot of this and I was like, oh, I like that.
Like just that character style, right?
So then it's like, OK, using thesame, I want to generate a new
image referencing the attached photo.
OK, I started there. So I wanted to see how that

(58:21):
worked. Then it was just like, OK, I
want to, you know, add more and more detail, but I want to like
create this same stylized look. So I had to create sort of like
that Jason code template for me.That way I could just change
these things out, right? And so it was like this stylized
3D the, the pose was a bust, right?
Because I'm not doing anything below the neck, you know, but it

(58:41):
breaks out all the variables that you can then change, right?
So then it was like, OK, cool. Like cuz all I had to do here is
like change the background color.
I want a different hairstyle. I wanted it, you know, I wanted
the tattoo, still wanted the female, you know, blah, blah,
blah. But I made all those changes
here. And then like kind of just kind
of kept going down this path andgetting into like animals,

(59:02):
right? And then I'm like, OK, cool, got
this. Then I want to come up with like
fun. This is where like chat, the
ChatGPT stuff is really interesting because it's like,
you can ideate right here too. And so then it was like, OK,
like, let me do, let me think oflike different animals, you
know, showcasing some sort of like, you know, funny or clever
kind of thing, right? And so it was like a goat with

(59:25):
like a crown, you know, blah, blah, blah.
And then I got into this part where I was like, dogs, I'm
like, OK, you know, like dogs kind of have their own
personalities by breed, right? Yeah.
So like, let me like break this down.
And this is where I used ChatGPTto like really think about all
the different dog types and maybe like what they would, what
their profession would be or what their personality would be
in like a human, you know, level.

(59:46):
Translation. So like this, this bulldog, you
know, almost like looking like alittle bit of like a gangster or
whatever. So then I had it like really go
into like Rottweiler club security, Chihuahua, LA hype
beast, Poodle, runway icon, you know, and so like it, it started
to give me some of those variables that then I could plug

(01:00:08):
in. But then I could take these and
say, OK, you know, using the Jason code, right, change these
variables out. So then I had to generate these
at scale for me, right? So I didn't have to go in and
manually change these every time.
I could just copy and paste, copy paste.
The whole list of the, the dogs that I wanted to run right.
And so, so then it started to get much, much easier to do.

(01:00:32):
So I'll just kind of like scrollthrough these so you can kind of
see. Oh see, like cuz that, that's
awesome. Right, like these are cool.
Any like these would be great toanimate.
It's just like, I haven't, haven't had time, but like these
were super cool and it's like, OK, the it's very consistent.
Type branding. This is if you want to go a
certain route with this. Yeah, right.
And so like that, don't sleep onthat Jason component, you know,

(01:00:53):
because that I think is the trouble, trouble troubling part
of like the ChatGPT is just likeyou're going to go nuts trying
to keep everything the same without it, without having some
sort of like binary aspect via code.
And and that obviously seems like that's one of the the
bigger unlocks with with ChatGPTspecifically in this, but.

(01:01:14):
Also low key token, token miningfrom that Jason code, There's
some good stuff in there. I saw there's like, you know,
Matlux finish, like there's some, there's some interesting
things, yeah. Yeah, this like smooth plastic
matte finish, ultra high resolution.
There was some good stuff from some of the stuff above.
I was like, huh, all right, thisis, you know, you could just
have a whole. And these were one shotted,

(01:01:36):
right? Like, so it's like if you really
wanted to refine these or make like I, I wasn't going to back
and forth with like tweaks or anything like that.
I I was more interested to see the success rate and the hit
rate, you know, and yeah, it's pretty dope.
Yeah, I like the, I like, again,the concept.
I can see that and take it and translate it.

(01:01:58):
Like if you're doing a branded icon set, like, yeah, like to do
those every once in a while, probably use the same exact
thing, right. That's.
But this is, you know, that was fun, dude.
I mean, and so I think that's that was sort of the interesting
thing with ChatGPT. It's like the the Jason part of
it. I think is is worth exploring if
you haven't already. Rory, you and I have talked
about that a lot, but I think that's one of the bigger things

(01:02:21):
that you can do. I don't know, do you have any
other thoughts on that before weget into mid journey specific
because I know we want to provide just like office hour
updates and maybe provide an update on the video part of
that. Let's just go right into the
updates. I think you know, the majority
has been in somewhat of AI don'twant to say a lull period since
Omni rough, but it's been like 2weeks.

(01:02:42):
It's it's charged like 3 weeks since they dropped it.
So, you know, something's comingup soon, but I think it's good.
To go, Yeah, you're right. Yeah, it's been, I think it has
been two weeks and so I'll run through these really quickly
again. Stop me where you want faster
version of V7? Plan to roll out next week so
that'll be next week. Check.
Cool cool. Love that potential minor update
with A71, but they're saying that they're likely jumping

(01:03:04):
directly to V8. There's an emphasis on
finalizing key personalization aesthetic settings.
New S ref planned so an improvedversion is nearing release with
a significant style transfer enhancement expected.
So I mean style weight like thatmeans that.
Or maybe that reskinning retexture even better, I don't

(01:03:27):
know. That would be a nice, I mean,
like, I guess again, we're we'resaying we don't want more
busyness and then we're also like, yeah, that'd be.
Cool, right. I think that's what we're
saying. I think that's what everybody's
saying, yeah, right. Initial launch won't include S
referendum. Boo Hoo.
OK. They haven't run one of those in

(01:03:48):
a while. I have.
I've been running them again. Yeah, I can.
Do it. And there's some good ones with
these, you can just tell they look a little bit more crisp,
more enhanced quality. Yeah, let's see what else?
OK, so here's here's what we're getting at, right?
This, this conversation, this episode's really been about
video. No surprise.

(01:04:08):
Then that video is like now seeming to come up more and more
here with with mid journey. Again, internal testing by
guides and mods beginning end ofmonth.
So we're shooting this the 23rd,so there's a week left.
I mean, so that's coming. You've got 2 video generation
methods that they're talking about, text to video and image
to video being optimized, multiple quality and pricing

(01:04:31):
tiers planned. So they're, I think their goal
here is to make sure that everybody's got accessibility to
it. They don't want to price people
out of the video component. Video quality described as
promising with distinctive aesthetic and excellent motion.
And a full launch. Launch is contingent on upcoming
server infrastructure upgrades, which are expected within

(01:04:52):
roughly 45 days. So you know, probably at least
two months away from like a fullroll out.
But I don't know if that infrastructure upgrade is a
blocker to launch though. Yeah, we've, you know, again, I
take this with a grain of salt. Like I wouldn't, I'm not

(01:05:14):
expecting to see this until later in the year, you know, say
two months. But I'm just guessing based on
where everything's at, you know,they'll probably put resources
back in. And then how fast are you going
to iterate on it once it's out? Because then, then you're in
this game, right? Then you're in the game of
runway video playing. You know, you're going to have
to, you can't just sit around atthat point.

(01:05:35):
You're going to have to have a pretty good velocity at that
point. I think they need a
differentiator. Right.
They they absolutely need a differentiator.
And it's not not like the video generators differentiator.
I think it's being able to like utilize mid journey, like mid
journey for the video, like being more creative with it, not

(01:05:56):
so like linear and sort of like rules based.
Like the camera moves this way and like, you know, you have to
do it this way. Like I want to use like click
style reference and then like you know something like that.
Or there you go, Rory. Yeah, I like that.
Pan left or pan, you know, like not I'm talking about like the,
the idea of it, not like the actual motion of pan left.
Like something like that where it's like it's always been.

(01:06:19):
They've always had a little bit of a different way of going
about it, you know, stylized chaos, you know, weird, weird.
Yeah. The way that everything sort of
like they think and and dream things up.
Like, I would love for them to be a little bit different in
that sense. So it could be fun.
Like I like the ingredients feature.
Personalization. That's still.

(01:06:39):
Personalization, it's like shit like that.
I don't know how long that'll take to develop but I'm I'm
looking for like one of those like X Factor features from
them. So I, I think, I think first
first impressions here have to be great.
They have to nail that first impression.
So there needs to be really strategic play around when this

(01:07:00):
comes out and it being right at the top at that very moment in
time when they leave, they release it.
So it has to be that I think it.Has to be easy.
Yeah, that that too. But like my thought there is if
you turn people off, right, they're not going to come back
and no, they're not going to come back and do that.

(01:07:22):
I think there are a lot of people though, right?
There are a lot of people that are using mid journey images as
the static to then take into themotion with these other tools.
So you've got an opportunity here.
I think they have to nail it with the capabilities and then,
right, like that speed of iteration and continuous

(01:07:44):
updates. And then lastly, to your point,
it's the differentiator. And I thought the way that you
describe is perfect, right? Like just be, just be who you
guys have been. Like you're going to have
something that no one else has. You're going to do it in some
other way that doesn't exist across another platform.
That's it. Those three things, I think.
Yeah, or we're not asking for much.

(01:08:04):
No, I mean, it's just some. It's just like the little extra
spice that they've always brought to it.
Not saying that needs to be in functionality, just like like
style reference. We didn't know we needed that
until we started playing around with the tool and then they gave
it to us. And it was like to me,
revolutionary because that was just so different than what
every other model was able to provide.

(01:08:25):
And I'm looking forward, I know they will do something like
that. I just want, you know, I think
they should also take the sort of runway model.
And if they're going to do this like they've done with V7, which
is just like release text to video first, let everyone learn
it, then go image to video, thengo the extra features, key
frames, then go whatever else you want to do.

(01:08:48):
Like I think that should be sortof like the way that they
approach it instead of like, here's all this crap.
Yeah, yeah. Like Sora, like here's all these
things you. Don't know about.
That's a really great point. I think there's going to have to
be a real focus on that too, more than they've had, right?

(01:09:08):
Like they don't typically do really big, big explainers.
They've they've done some littleone or two-minute clips on a new
feature here and there. But I think you're right.
There's, there's got to be, there's got to be that.
It should be make it easy for everyone.
Like again, you said you have you have one shot at this really
with people they're not going tolike just with the other tools

(01:09:29):
that are available and like how complex they are now at this
point. Yeah, there's got to be some
level of simplicity or magic, right?
Like the? Magic, I think.
I think that magic really is thedifferentiator.
Yeah, really is 1. 100% and still can't get anything that's,
you know, mid journey imagination quality on any other

(01:09:49):
tool so. Very true.
Until later time, I will not be,I will not be abandoning them
because. Yeah, man.
Yeah. There, there is no, there is no
other tool that has that magic. And I even with these more super
coherent models, I said this like 70 times, but I'm just not.
I just don't want to control everything anymore.
Like I don't, I don't want to prompt that much.

(01:10:10):
Yeah, yeah, it's too, it's too much thought and too much
frustration. Like I just want to be able to
to go in there. Speed matters.
Speed matters. Quality matters.
Yeah, taste matters, you know. And some of them want new ideas
like I want mid journey to spit out 30% of what I didn't.
Prompt, of course, dude, I thinkthat's that to me is just a very

(01:10:33):
like, I'm surprised more people haven't uncovered that.
Yeah, part of that, yeah. Because we don't always like, we
don't always know what we want. You could like default same if
you have like customers and you're building products like
you have a pretty good idea as to some of the things they need.
But sometimes they don't know what they don't need or what
they need. So, you know, there's that level

(01:10:56):
of like, Oh yeah, right. Like this does make sense.
I wouldn't have thought of that.Like text, like text and images,
we didn't know we really wanted it.
And then ChatGPT comes out with it.
We're like, OK, maybe we wanted it.
Yeah, maybe. We wanted that 100%.
But I think it's just the exactly.
I'm not going to go too much deeper.
So I mean, we'll, I mean, we'll see what happens, right?
We still got plenty of time to talk about it.

(01:11:17):
We'll see there. There are a couple other notes
here we'll just finish up with. They're planning some UI, UI
improvements for Pro users, particularly targeting higher
resolution monitors, 4K monitors, evaluating batch
processing features for premium tiers.
Yeah, we haven't seen that batch8 yet.
Remember that was talked about that got deprioritized

(01:11:38):
enterprise and API considerations.
I've seen that come up a lot lately.
So it looks like they're finallytesting that.
And then I think they're going to do, it sounds like they're
going to do a survey too to maybe gauge that interest, but
got to, got to. Do it, God damn it.
So let's just do it. Yeah, I so near term priority.

(01:11:58):
OK, here are the priorities. We'll just kind of recap this
and then we'll we'll wrap this baby.
So immediate focus releasing faster V7 proved SRAF multi
subject referencing features. Yeah, don't forget about that.
Right, Which one? Multi multi subject referencing
features. So multi Omni ref, right?
Like yeah, that's common multiple objects.
So then you got subsequent priorpriorities would be launching

(01:12:19):
video model, server upgrade, refining user personalization
tools, long term dev, exploring voice modes, advanced UI
features and broader creative tools which would be your
software, hardware things, secret projects that we don't
know about. I don't want to hear about a
secret project anymore until until I see it.

(01:12:39):
Same same. It's like, it's like your friend
keeps coming over and it's like I have a secret to tell you and
they're like, what is it? They're like, I'll tell you
later. I'll tell you later.
For like 2 years, yeah, whatever.
I know there's a secret. Just yeah, just don't even tell
me. Yeah, just let it be a secret.
But dude, it's still like reallyamped about what's coming

(01:12:59):
because I feel good about this dev schedule that it is.
Feel like there's something coming at all times and not.
Just like that. That V6 wall where it's like
when are we getting V7? You know it kind.
Of felt like the back, the back half of last year just kind of
felt like it dragged on a littlebit.
Dragged now it feels like they're they're on a little bit
of a tighter ship and I'm I'm appreciative of it.
Yeah. It's it's good for us like we,

(01:13:22):
we need to be. Go mid journey, go we we do.
We do love you guys. I mean, the, the product's
awesome. Obviously we do this podcast
primarily based on mid journey, so we, we do feel very strongly
about it. But yeah, it's exciting to see
all this stuff kind of to happenand continue to compound, man.
I mean, this is we're living in wild times here.
Who knows what's next? I don't know.

(01:13:43):
We'll see. It's all, it's all chaos,
people. I get that question so much.
Like, where do you see this in six months?
I'm like, I don't know. I just don't know.
I don't have the answer. I can't predict it because it's
too crazy. And then companies are really
smart, man. They're just getting better.
They're getting better at understanding what to do, how to
launch things, what people want.Like there's more mass opinion

(01:14:05):
out there. There's more data, you know,
data to pull from. So we're moving, baby.
My man dude, it's good to catch up.
I mean God felt long overdue. We've been, we had to take a
couple like 2 week breaks here because we had a bunch of stuff
going on. But man, this is a good one
guys. I mean like we covered, we

(01:14:26):
covered a lot. Thanks for joining us.
We'll have something fresh for you guys on the next one.
And Rory, you got anything to say?
Wrap up like and sub or comment.You guys are awesome.
Last video too, commenting, dropping a bunch of stuff in
there. You know, again, tell your tell
your wife, tell your mom, tell your friends I'm hanging out.

(01:14:48):
It's a good place for us all to have a therapy session so.
Global Community. Yes, Sir, and thank you.
Thank you very much. With that, alright guys, we'll
see you in the next 1. See ya.

All Episodes

Episode Transcript

Popular Podcasts

Stuff You Should Know

Paper Ghosts: The Texas Teen Murders

Dateline NBC

.css-15opob5{left:0;position:absolute;top:0.8rem;} All Episodes

.css-14f5ked{margin:0;word-break:break-word;display:-webkit-box;-webkit-box-orient:vertical;box-orient:vertical;-webkit-line-clamp:2;overflow:hidden;}Veo 3 Makes Yesterday’s Best Look Like a Beta Test + Runway & Midjourney Check-In

Episode Transcript

Popular Podcasts

.css-r6mb8g{margin:0;word-break:break-word;display:-webkit-box;-webkit-box-orient:vertical;box-orient:vertical;-webkit-line-clamp:1;overflow:hidden;}Stuff You Should Know

Paper Ghosts: The Texas Teen Murders

Dateline NBC

All Episodes

Veo 3 Makes Yesterday’s Best Look Like a Beta Test + Runway & Midjourney Check-In

Stuff You Should Know