Midjourney Video is HERE—Nerds React + New SREF System Chop-Up

Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
(00:00):
What's up everybody, mid journeyfast hours podcast episode 44
and Rory and I were just sittinghere talking.
We were just like, man, what arewe?
What are we even going to talk about this week?
Like nothing has happened. Like like not like there's been
a video model drop, not like there's been like a new SRAF
system drop, not like mid journeys just shipping out of

(00:21):
their freaking minds right now. Nothing.
So dude, this is I'm super pumped for this one because you
know, like there's always like acouple of those weeks where it's
like, you know, small changes, what are we going to bring to
the table? Right.
And this one, I mean, dude, thiscould be fucking for our podcast

(00:43):
if we wanted to be. Probably.
We won't do that to you guys, but we did bring our drinks.
We're going to do we're going todo a little mid journey after
dark. We're shooting this a little
early. We're doing this on a Thursday
night this time and yeah, we're going to go on the weekend
strong and just kind of play with, you know, all these new
updates. I mean, just so many new toys,
new shiny toys. Basically just like a emergency

(01:06):
podcast on a Thursday, we fit itin because we had to had
couldn't couldn't wait around till Friday for this one.
We need to get it out while it'sfresh and if you can hear my mom
laughing in the background, that's I can't with those I.
Can't but I want to. It's like I don't know what my
dad just said. I'm at my parents house.
I don't know what he just said but she is like borderline pee

(01:27):
the pants kind of laughing so. Yeah, damn, your dad still got
it then. They, you know, he'll throw a
zinger and when every once in a while.
I wouldn't say that's that's 100% of the time, but yeah.
Man you get you get your wife laughing after that many years
bro, you still doing something right?
I, you know, you work for those moments when you get it.
You just yeah, did it. Yeah.
'Cause you swing and miss probably 9 out of 10 times.

(01:50):
That's true, dude. I I say so much funny shit my
wife won't even crack smile. I'm just like.
Man 100%. Come on, it's 'cause.
It could be the funniest thing, but the wrong time.
That doesn't make a difference. If it you could, you could have
the banger of a of a, you know, a line.
And if you know, if the girls are like, you know, doing
something crazy in the kitchen or like, you know, my wife's

(02:13):
like changing a diaper, like there's no like at the in one
ear out the other ear. I didn't even hear it.
I'm like, well, now that's gone into the ether forever, never to
be spoken again. But I know it was a killer, so.
I mean, you know what, you know when you got a good one, you
know, you just want to see it, You know, just just a little
bit, just a little something, something.
You know, it's, you know, I'm pretty sure my wife's probably

(02:35):
pissed off at me after just likestopping our day yesterday.
Just being like, that's it, yeah.
What were you? Yeah.
What were you doing yesterday 'cause I text I I just happened
to see it at the right. It was like one of those right
time things 'cause you know, I've I'm doing shit during the
day. But like really saw an up.

(02:56):
You know, like I just saw this update and it literally just got
announced like 3 minutes ago andI'm like whoa like.
You know and. And it's still cool the way that
mid journey to drop it because it's like a whisper in the wind.
You like it's like news the old way.
You know, it's like the Pony express to some degree.
You know, it's like you get it when you get it.

(03:17):
No blast, no big like revealed, no giant, you know, demo video
showing like all this crazy stuff.
Just drop it on the website and then like you tell someone and
then someone tells someone and then you see it on Twitter and
then like it just goes the most organic way.
And that's the one thing I will say about this is this is the
most organic release I think I've experienced in a long time

(03:40):
where I got excited again, I wasexcited about VO3 when I started
using it. I didn't feel this like I I felt
like awesome. I don't know what how else to
say it. When I started hitting the
button, I was like, this feels like version 4, like sort of
like the unknown. What's going to come out of it?
Is it going to be good? And then when it hit, like right

(04:02):
away, I was like, oh, thank God,you know, like it just is just
like a wave of relief of like, yes, all right, we're back in
it, baby. We're.
So fucking back, dude. OK, listen to this timeline.
All right, so round one, video rating party, June 11th.

(04:22):
Video rating party round two June 13th.
Real video ranking June 15th. You got me excited with that.
One and that's when I was like oh fuck 'cause I didn't I didn't
read all the fine print with that right.
So let me like just kind of showyou guys what we're talking
about here. But you know, just going through
the, you know, the updated noteshere in mid journey, right,

(04:43):
which you can access just on updates here.
But I was just like, oh, real video ranking.
Click here. And I'm like, oh, dude, what?
So it was like, this is like prerelease ranking.
And so I went into those and those were it was just like,
boom, yeah, boom, boom. And I was.
Like, wait, no way. I was like, this is real.

(05:03):
And then then I went back and read the five.
Yeah, I texted you. I was like, bro, wait, what?
And you're like, no, dude. No, no, no, no.
They're just read it, Read it. I was like, oh, shit.
OK. June 15th, June 16th, video
pricing survey and then you get the the style references, the
new update also June 16th, yeah default model.

(05:26):
And then all of a sudden you getvideo on the 18th.
Like dude, that week was just nuts.
But like can can we just talk about like this is Mid Journey's
side project essentially like video as it seems.
But yeah, there's a really good,so there's a really good line in

(05:47):
there, which is what we've mentioned in here on this
podcast a few times. If they want to get to like real
time world building simulation, which is where they've always
said they wanted to go, they were like, we have to do this in
steps and we have to do this in layers.
So we said we definitely talked about this where I was like,
well, you start with images and then you go to motion, which is
videos and then you go to 3D andthen you go to, you know, so

(06:10):
then you go to 40. So they they said it like that's
the timeline, that's what they're building towards.
So this is just a step and that what seems like a side project,
right? Like this is damn good.
What? You meant dude.
It's funny that you mentioned that because I was just reading
this right. Like going back to the office,
hour notes, goal images, video. Real time 3D integration within

(06:33):
one to two years. OK, long term vision, real time
open world simulations with interactive environments.
Yes. Right, this is, I mean these
these two lines here pretty mucheverything you need to know.
I'm confident they can do it now.
Like after this. Like, this to me was like a
litmus test for the future. Like if it came out and just was
like Sora and it was like, all right, this is hard and it

(06:54):
doesn't work ever. And it's just not fun.
I was like, this isn't going to be good for them, but.
Bro, they unbelievable though, like great V1.
I mean, I'd I'd love to like, you know, I'm, I'm sure you and
I are just like, let's share some examples.
Let's share like first impressions, strengths,

(07:16):
weaknesses, like, you know, obviously like like let's
dissect this a bit. Definitely.
There's there's so. Much to get in give me give me
first pure raw insight based on like your first time playing
with this. So taking you back to that time
where you just jumped in right and then you you said there was
a little bit of that surprise element of like and and look, we

(07:39):
were talking about leveling the expectation, right, Like we had
just talked about that we're just like, well, look, I think
we're both in the same camp of like we expect good but not
great. Like we know there's probably
going to be some stuff so let's not get our hopes up too high
kind of thing. But like, where's that landed
with you now, now that you've had some time to kind of like

(08:00):
play with this thing? There was, if we go back like
what was it 2-3 episodes when wewere talking about can the
journey compete and video, therewas like really two things that
I wanted from it and I stated there was one I wanted the mid
journey factor, which was like, you know, I call it the mid
journey factor, which is just like, can the journey make this

(08:21):
easy and fun? Number one, they nailed that
with auto prompt, right? Like, yeah, like that's the to
me, you can go on the only tool you can go on and type in
picture of a car and get an awesome picture of a car.
And now you can just hit auto prompted.
You can have a really cool videoin less than, you know, 2
minutes from was it a really good aesthetic without having to

(08:41):
go and prompt 6 paragraphs right?
To me, that was massive. Like the auto.
I didn't know I wanted auto prompt until it was there and it
worked and I was like thank you for.
This. I like the, I like the two
variations that I think that's we go back to looking at the
video rankings when we were saying why is 1 video super

(09:01):
still and one video? That's right, Yeah.
You called that out. Low motion, fat, high motion,
right? So do you have those two?
So I was like, all right, this is great.
Now the other side of it was like we talked about how they
could win and it's if you could take mid journeys like very
distinct aesthetic or the crazy shit that you can't animate in

(09:23):
any other platform. And if it can do that, then like
it's going to keep us all and we're all going to love it
because no other platform can dothat.
Nailed it. Like they just totally nailed
it. I went right to the like the
most complicated images I could find and was like, let's see and
hit auto prompted first shot. I was like, all right, here we

(09:44):
go for all the complaints about mid journey being hard and
there's so many parameters and there's so much stuff now does
it get any easier than auto prompt and you get a great
video. I get some people want control.
Most of the time if your image is is constructed correctly or
prompted correctly, it's gonna auto prompt.
Well, so like it's gonna get basically the only thing, the

(10:06):
only like a few things that it can do on some images, right,
But. Yeah, yeah, I think that's,
that's what I've noticed becauselike I've I've you know, to
where I'm at right now is I've basically tested really short
prompts and mostly done, you know, the auto I I've run some
manual obviously like just see how it works.

(10:28):
But like, to your point, I haven't really gone into more of
the the like very specific, complicated sort of prompts to
see how that maybe varies in in the results.
But I would say like in general,I like how approachable this is,
right? It's, it's not, it is not

(10:52):
intimidating at all, right? Because you go in here like let
me let me go back to my, you know, let's just go back to
stills here, but let me scroll back a little bit.
I was loving just kind of doing this particular S ref.
I was just really loving this S ref.
I was doing yeah. So I was just kind of like going

(11:14):
through and like, you know, simple animating these because
basically these are all very simple prompts.
Because the way that I unlock S refs, which we'll also get into
right, is like I, I, I use like either a phrase or a single
word. And I found some that like
really kind of work well with different S refs to kind of give
me an idea of if I'm going to like it.

(11:36):
And so these are very, very simple ones, right?
But you know, like just clickinginto this and you know, for the
first time, just seeing like, Hey, I just got four options
here, right? And you know, low motion, high
motion, it's easy to understand based like it for for me, for
you, for most people, I would imagine it's like it's pretty
easy to understand when I would want to use low versus high,

(11:58):
right? So I like that idea of like
little and a lot, right, based on the scene, because like, if
you've got something very like still and stagnant and something
like this static, it's like, OK,well, I'll probably use low
motion. I might run high motion to try
and see what what happens, right, Because out of curiosity,
because we're experimenting, butlike, you know, I love that.
And then let's talk about let's fucking talk about the fact that

(12:22):
you get the four, the fucking 4 grid, which no one else is
doing, and you get all of them at the same time.
I'm not saying it's, I think there is something there from a
user experience standpoint that needs to get tweaked, right?
Because your eyes can't focus onall four at the same time.
So that's the challenge, right? It's like, because what I want

(12:43):
to do is like, as I'm trying to quickly move through these is
kind of like take a step back and glance at them from far away
and just kind of see, follow theone that feels right the longest
until it falls off. And then I'm like, oh, OK, not
that one. And then I got to go back and
kind of watch them. Yeah, but I mean, the fact that
you're getting four, bro, what the fuck is this?

(13:03):
This is awesome. Awesome, awesome, awesome.
That was the way VO2 was when I was beta testing it, and I'd get
4 every time. And it was, it was amazing
because you'd get like one to two that were like exactly what
you asked for. And then maybe 2, two of them or
one or two of them was just likea little bit off, you know what
you asked for. But it would sometimes a lot of

(13:25):
the good stuff will come from those two now, Like if you're
looking at the, the one that youhave hovered over, right?
Like the one that has the exploding background, like that
would be the variable one, right?
It's, that's why it's nice to have 4:00 because I think it
could be like, I didn't ask for that.
That's what I want. You know, it's cool.
Now I like that. I want to play with that.
So do the four, the having the four is great.

(13:46):
The other thing I think there's that's that's interesting to
note they didn't do like a separate tab.
It's all accessible within the create.
Which is. Super nice.
I like that. I like just being able to click
it. It's all in the same place.
You can then, you know, sort by video.
As you can see now we're doing that, but that's a simple that's

(14:07):
a simple, subtle thing that like, I was hoping it wasn't
like editor. We're always going to be in like
its own dedicated space and I was going to have to jump back
and forth and then like, you know, so it's nice the way they
did it and I'm happy they did itthis way as they normally tend
to make things simple and it doesn't get much more simple
than having four buttons and that's about it.
I love it Yeah, I love it. It's a great first start, right,

(14:29):
because they did kind of cater to maybe people that that really
haven't been generating a lot ofvideo, right?
It's like this is this is very approachable.
Again, like I think anybody could appreciate this.
Look, you want to go ham, you know, get into the extend the
video or the you know, portion where you're actually, you know,
text prompting exactly what you have that option.

(14:51):
You're looking for something just kind of experimental or low
effort, right? Or just ease efficient.
Just do the manual. And like I've been testing that
out specifically too, because I wanted to kind of see if I could
identify certain patterns. Yeah, in, in what comes back.
And I'm curious to see if you'vepicked up on anything so far,

(15:12):
because I've, I'm seeing a couple things that I, I've
noticed, for example, like anytime there's like somebody
like this and the motions high, they always turn around.
Yeah, always turn around. And then there's like, you know,
like whenever you get into like some of these slow motion ones
too, it seems like they're, they're very similar slow
motions. I think they're almost like slow

(15:32):
motion template kind of movements because I, you know,
like, yeah, because like some you kind of like you see the
rotation, some you kind of like they kind of jitter back and
forth and then, you know, like others, I don't know, just
something I've noticed. Like have you seen anything like
that on your end or what other observations like have you kind
of taken away from from what you've seen?

(15:54):
Well, that one, definitely, yeah.
Again, going back to whatever episode we did on this one where
it was we were talking about images for video when we talked
about that, where it's like if you have motion baked into your
images, it it's you're gonna youalready have a leg up.
So like I try to lot with the motion blur background or some

(16:14):
sort of like, you know, like people are already like half
running in motion or a car is like speeding and you can see
like that, you know, tires are spinning and there's motion
blur. So it's like it just like takes
it and runs with it, which is always what I've always what
I've appreciated. But there's there's a creative
factor to it, which is why, you know, again, I feel like I'm

(16:36):
highlighting like 50 episodes here.
We talked about this. I know man.
Sort of like Apple, right? We went back to a long time.
We're like mid journey feels like the Apple of this whole
situation versus like, you know,when we were talking about it
was like stable diffusion like this is that's how long ago it
was felt like the PC version or flux now feels like the PC
version, but the there's a creative edge to it where you

(16:58):
don't have to control everything.
Every other platform is focused on control and the journey says
we do the other way. But we'll just, we'll just, you
know. It's a great observation.
Push a button and it'll work, which is why, you know, I don't
want to think Sometimes I don't want to write totally three
paragraph prompts to get something cool.
Now I just hit high motion and bang, I get what I'm looking

(17:19):
for. Like that's awesome.
So again, this is like A and andwhat what also can't be
overstated is how hard some of these images are to animate like
and how hard it is with motion to keep that style consistent
beyond the initial frame. So anyone's not familiar with

(17:39):
running, you know, image to video on a lot of these other
platforms. If Drew was running an image
like this, you know, maybe priorto you know, cling to and VO3
and you know some of the new developments, if you wanted to
move off of that frame like if you wanted as like pan left
yeah, a lot of times that style would not transfer mid journey

(17:59):
style would not make it to the rest of the video because it's
just too complex and the video generators are just like I have
no data on this so I can't I can't compute runway notorious
for that. Kling's pretty good at keeping
consistency. Mini Max was always pretty
decent at that, but like you couldn't throw a lot of this
stuff into VO3. Like no, no shot at VO3.

(18:20):
I think it's revolutionary and awesome.
Just some of this stuff just doesn't work in it.
It doesn't have data. So like that is to me also, like
again, we were talking about where they could win having that
style and being able to animate something like this, right?
Like that's where I'm seeing just massive improvement.
And I think if you look across, if you open up Twitter, if you

(18:41):
open up LinkedIn, TikTok, whatever, you're going to find
people that are amped about thisbecause they have all these
crazy images that they're like, this makes no sense to put it in
a story, right? Whatever.
I just wanted to see what it looks like moving.
And now you can do that. So it's a great point.
Yeah, it's a great point. Like this is again, one of those
moments in time to go back into the archives.

(19:03):
Deep, deep into the archives. Don't forget about all those
great things that you've alreadycreated.
I'm talking to myself. I'm talking to you, talking to
all of us, because dude, that's I mean, we've we've already
create, we've already done the legwork on so many great images.
We owe it ourselves to kind of animate and kind of see where
these things take us. I also really like this idea

(19:28):
here with like the S RAF combination with the video, you
know, like that's amazing, you know, like the fact that you can
really, you know, get different and weird and unique because
there are so many different S ref codes.
There are so many preferences that you may have, you know, so
like I'm going to go back and you know, look at some of those
S ref codes that I really like and you know, these were fun

(19:50):
like I mean, these were the first ones I tried out with
video. So a lot of this wasn't
necessarily realism, but like I just love seeing like this felt
like a world to me, right, because now it's it's the it's
the S ref and you, you know, yougot great stills, but now.
You know, with the motion added,you're almost kind of creating
this little world, right? Because you know, you could take

(20:10):
any one of these and start to like connect the dots and, and
make this like its own little neighborhood or, or ecosystem,
right? In a way.
And I think that's, I think that's pretty neat.
I I would say so I think it's also like if you can't sort of
drew up a world for yourself andthe journey can provide AS
referendum world for you. So that's.
Another. Thing again, yeah, like that's

(20:31):
like personally, sometimes I just don't want to dream up a
world to like sometimes I just want to see what it can do and
where I can go and I want to play off it but like as
referendum perfect for that, youknow it's like there's it's like
forced creativity like I'm I'm not maybe I'm not creative in
the moment, but I can get there with some with some help.

(20:51):
But these are really just like overall first impression,
expected to be let down, not letdown in any shape.
Or form, yeah, like really solid, good first look, you
know, and. People think maybe that like
we're being over like over emphasizing it.

(21:12):
I think it's just from using allthe other video models so much
and knowing what's hard with them and knowing where like the
rough edges are and coming into this and pushing one button and
getting good work out of it. It's like, it's a lot like it's
a lot of thought that goes into the video stuff to make it good
and just to have one button and it works and it works with the

(21:33):
crazy stuff, you know, like that's it can't be understated
with. And I think you saw, I saw so
many people back on, you know, Idid a post on it on LinkedIn
yesterday. So a lot of people that came out
of the woodwork that I hadn't seen on my post in a long time.
How interesting a. Lot of people that were like so
amped about it. I think there's like AI said,

(21:54):
this is someone yesterday, I forget who.
Maybe it was. Maybe it was our buddy men.
I was just like, I like feel something again for a.
You're no longer numb. I'm no longer numb.
I was like, I feel it again. I'm like, oh, I'm like excited.
I was sitting around waiting to play with it today while I was
sitting in four hours of traffic.
I'm like, come on. Let's go, man.
Yeah, brutal. Whatever mid journey is better

(22:15):
than traffic. Guarantee that.
Take that to the bank. So, you know, tell me this too,
because we're we'll, we'll kind of like preview kind of like
what's next here, because they did announce kind of like what,
what they're working on next with this.
But any like where, where do yousee the shortcomings currently?
Let's I mean, obviously we're looking at this V1 model just
released. So I mean, we're not going to

(22:36):
sit here and blast it, but like where do you see the
shortcomings currently here in terms of like, you know, short
term improvements that you wouldexpect to happen?
Shortcomings is a few. Number one, I think it's
interesting that they chose A480P route instead of a 720 or
1080. Personally, if if that's what it

(23:00):
takes to keep the cost down and give me 4 generations, I'm
totally cool with it. Like 480P, it says it's 24
frames per second. I don't think it is 24 frames
per second. It kind of looks a little bit
choppy in that regard. But like, those can both be
fixed. Like if the quality keeps up

(23:22):
with the way that it is, the motion, the coherence,
everything else I can sacrifice to the 480 now because, you
know, we highlighted this on theepisode last week on Topaz
Astra. Now I can run that through get
1080P it'll be crisp or does regular Topaz video AI up the
frame rate up the resolution totally good.
So like if that that's what allows me to generate more

(23:44):
videos here of the things that Iwant to play with totally fine
with that. How?
Much is how much is Topaz Astra?Topaz Astra.
I'm not exactly. Sure is that Is that a license
or a subscription? So I worked on that product, I
gave the team a lot of feedback on it.
I was working on, I worked on Starlight with them, which is
their original upscaler. If you're not, if you're not

(24:06):
familiar with Astra, it's Topaz's new video upscaler that
is specific for basically AI video, adding more texture and
detail, but it's built off of Starlight, which is like the,
they're like initial diffusion upscaling model.
So it was the first diffusion video upscaler, but Astra's

(24:28):
great. It's easy.
I don't know if I, I think I have some, you know, being
honest, I have some free creditsfrom being, you know, tester,
giving a bunch of feedback and like playing with a bunch of
stuff. So I, I did buy the Topaz video
AIA while back, whatever that was, whatever that cost.
The one time fee is like 300 bucks or something like that and

(24:49):
I use that all the time. But Astra now has been really
good for, you know, they're trying to be magnific for video
and, you know. Yeah, interesting.
Yeah, good, good pivot for them.Yeah, Yeah.
So. Professional products are
awesome, not just like AI stuff like their stuff for video
itself is great. Like they, they have really high

(25:10):
end products and they're really.Yeah.
I mean they, they had, I mean they were, they had a lot of
photography tools. I mean they, I mean, they still
do. But that that was how I got
introduced to them a long time ago.
And they had one tool in particular that I had a license
for. And I'm the name is escaping me
now, but it was particularly good and I liked it for one.

(25:32):
Really good. No, was it?
No, something like that. It's going to drive.
It's going to drive me nuts now.But what it did was it it had
this awesome little thing at that time, which none of these
other ones did. And it was basically like this
micro contrast and tonal contrast sort of like function

(25:56):
that when I was doing a lot of portraits with my photography,
it allowed me to get so much detail on the face, you know,
and it just, it had like appliedcorrectly just it, it took the
images to the next level. I would literally spent money on
just for this one thing. And man, that like loved that.

(26:18):
Like it used to bring out the pores.
And so I like I did this series too, where I was taking photos
of homeless people with, with their permission.
I wasn't being an asshole, but like I was telling their
stories. And I ended up turning this into
like this whole fundraiser thing.
It's a story for another day. Actually.
It was like a really cool thing in the long run.

(26:38):
But like the the those types of people typically have a lot of
character on their face. They've been through some shit,
you know, they're not in the best condition.
They're probably, you know, one of the worst versions of
themselves probably in that moment, right?
Like they're very vulnerable. But it's it, it shows up on her
face, right? And so it's like a tool like

(26:59):
that used to let me dial it in and pick up all these little
like all these little micro wrinkles and pores and, you
know, imperfections. And it was just like, man, I
just took the images to the nextlevel.
So Topaz is like somebody I've been familiar with, but I
haven't haven't been keeping a close watch on it.
But it sounds like they've really pivoted well, you know,
with with the AI stuff in particular and then obviously

(27:22):
like with the upscaler stuff too, obviously even with the
image Gen. It's good.
Well, they just, they just introduced Bloom, which is their
competition to magnific, I will say.
OK. I did see Bloom, but I didn't
know what it was. So that's that's the direct comp
to to magnific. OK, got it.
Good. Wouldn't say it's magnific yet,
but I'd still think like their video upscaler is like the

(27:45):
product for the time. And I said that to the guy that
I've been working with today. I was like, did you could you
guys couldn't have launched thisat a better time?
You're going to have 2 million people creating videos and
they're going to want to upscalethem because they're at 480P.
It's just like right product, right place, right time.
Like this is, you know, Astra's and Astra.

(28:06):
Again, the one thing that I willsay is that it still softens
things out a bit, which, you know, smooths them out a little
bit too much while adding a little bit too much contrast.
I think if you have a relativelydecent looking image or video to
start with, it's going to be great.
If you have something that needsa lot of work, it's going to
smooth it out. So just no.
Interesting that's. Just my that's sort of my

(28:29):
analysis of it. This one.
Oh, you get some free credits here.
So there's this one with bloom. I was like, it's quick, it's
easy, simple. I thought, I thought I'd overdid
some stuff. It's like magnific when you hit
too much, too much fractality onthings.
Yeah, that always drives me nuts.
I hate that. Yeah, you know, because you have

(28:51):
to like dial it in so precisely to not get the artifacts and you
know, and and there's almost like too many options then
because it's like, oh, you know,I like using the God.
I haven't even used magnificent a couple months now.
But you know, it's like you've got those different models, then
you've got the different types of photo.
It is right. Is this art or illustration?

(29:12):
Is this video game is, you know,so it's almost like it's it's
great to have options, but it's almost like too many options,
right. And then you you run into the
fractality of the HDR stuff and you know, you have to find this
perfect balance. So.
Which which you know, whatever, but I did see that magnific
magnific upscale generations didget faster.

(29:36):
I did see some news on that. Javi was doing something too.
I saw him tweeting about something.
I don't know what it is, but he seemed pretty excited about it.
If anyone's not familiar, Javi'sJavi Lopez has a great follow on
Twitter. He's the one who created
Magnificent and he's always testing everything.
But the other thing now that yousay, going back to just jog my
mind on the sort of the maybe the rough edges on mid journey

(30:00):
on the, on the you know what, maybe I'll share it.
Cause a few things I noticed andit's probably very similar to
what you've seen with other, with the other video generators.
There's a ton of things that seem to be the same and
different at the same time. But let me see if I find the
video like like cars, for example, right Cars, if you

(30:24):
don't specify, they sometimes just end up driving in the wrong
direction, right? So like this one, that's
something that happens in a lot of, you know, other video
generators unless you tell it. So I pushed auto prompt on this.
I got 4 cars that are moving backwards now that's something
that's going to happen a lot if you're not familiar, you know,

(30:45):
with how these things work because you know like I just
push auto prompt. Why didn't it work right?
Like that's how a lot of these things happen.
Here's another one that's standard.
I I went back and used an old mid Journey 4 image.
But a lot of times you'll get static wheels, right?
This is something we talked about a lot.
If the wheels look like they're static in your image, a lot of
times they're going to end up looking static in your video.

(31:08):
So this goes back to like prompting, you know, for certain
specific items, like you're going to want spinning wheels
like this one. It actually did it.
But I think there's basically, you know, see two of them, two
of them have no spin. It just looks like the car's
gliding, right? So simple like things like that
that have always been prevalent,right?
Like I've always, I'm noticing that.
The other thing is, you know, there's.

(31:31):
So I'm interested. There's actually some decent.
I was playing around with this one.
This is an old like V6 image. I was like, oh, can we do fight
scenes now? Not bad.
I mean, like fight scenes are pretty shit to begin with.
But this one, I was like, OK, like I, yeah.
Passable. I can screw with that 'cause

(31:52):
that was a that's a complex image, right?
Like this isn't something that'ssuper simple to animate.
There's a lot going on. There's, you know, all the all
the water splashes. We we did touch the background.
We we touched on that a little bit like just kind of like
thinking about, you know, we sawthe rankings last time.
I think that's where we were at,right?
Like we saw, I can't remember ifit was one or two, maybe it was

(32:13):
just one that first video ranking party.
But we did say look, hands, hands and body movement already
looks better than the stills. Yeah, right.
Like you're like the the physicsof this are already better,
which then again, I, I, I don't really know how it works, but it

(32:34):
feels like, OK, well, if you've unlocked that with video, you
should be able to apply that nowwith statics.
Right. So the interesting thing is that
if you have messed up hands in an image, the hands correct in
the video, which is I've never had an issue with hands in
videos really like I don't know what it is, but for whatever

(32:54):
reason, they they correct, they auto correct themselves.
Like let me see if I can find the example of that.
Maybe it's it's one of these, I forget which is the good one
that I that I utilize. But like her hands are totally
jacked up in this like in the inthe image, but they they sort of
correct here. Maybe that's not the one.
See how they kind of like auto correct there?

(33:16):
Like they they're kind of they were like a messed up.
Yeah. See how they're see they're kind
of like screwed up here, Jangled.
Like jangled and mangled. But when you come and actually
like look at the video, the hands sort of just auto correct
themselves. So like hands again, I don't

(33:38):
think you have to worry about them as much.
This was also impressive that you could spin someone right and
then you come back and then the faces are the same most of the
time. I think I extended this one, but
that's, that's another thing to test, like if the models are
good or not, like we'll keep thesame face as they spin or as
they turn. Cause a lot of times it'll just

(33:58):
regenerate to something else, right?
Like it'll be something totally different.
So that was one that I was pretty damn impressed with.
Again, that's like little tests.And then there's certain things
like, you know, like, can I justgive it this?
And it just. I love that one, yeah.
I I gave it a magazine cover that were not at least a mock
magazine cover that I. Made That's sick.

(34:20):
So just again I. Mean look at that.
Look at that movement. But the movement, the movement
and the pacing of it looks perfect.
Notice the camera shake when he when he hits the ground right,
like certain things like that where it's like he steps up or
maybe it's this one. No, it's not this one.
I think it's this one when he like stomps you see like the

(34:41):
camera like bounce. Up and down, that's what I was.
That's the one right there. Yeah.
Hey, tell, tell everybody like how you're, let's talk about
organization for a second, because now this adds a whole
different layer of how, how you going to track the videos you
really like, you know, along theway, right.

(35:04):
For me, my process now is it, ithas to change with the video
thing because right now there's no upscale option.
So that was how I was sort of like, you know, separating the
images that I really liked from the images that, you know, we're
just was I would upscale them and then that's how I would
filter them in my archive. Now with video currently not an

(35:26):
upscaler. Important to note though,
upscaler and higher quality. That's in depth.
So I would that like that feels like the next thing that they
would pump here for video. So that's going to be
interesting, but how are you kind of going around and, and I
guess separating the videos thatyou like For me, I've had to

(35:47):
pivot and then like, you know, you know, actually like heart
the the videos that I'm liking and then that's how I'm going to
sort those. But are you doing it any
differently or how are you thinking about that?
I'm being sort of selective withthe videos right now, like I'm
only doing the ones that I really want to see.
Like I didn't just go nuts yesterday.

(36:08):
I was like I, I had like a bunchof images that I wanted to test
like I want, I knew like I wanted to test this one and see
what it could do, which I was like really impressed with what
happened on the viewfinder. So I'm probably just going to
start to like this stuff now. Like I haven't even thought
about it, 'cause like I, I knew I wanted to see what this stuff
could be, You know, like this one to me was like this sort of

(36:28):
entirety was crazy that I just took that 2D.
Animation. And made that like we had a
little bubbles flying out the back.
I'm like, this is great. So I don't even know, man.
Like it's a great question 'cause this is, I was so just
dialed into to finding like it'sso weird.
I was like finding the things that I wanted to go back and

(36:49):
wait. Just in case anyone's hasn't
seen this, we have a little, youknow, Drew is now.
Oh. My God damn.
Holy shit. I had to get I had to, you know,
I like created that video and I sort of snuck both of us in
there just being, you know, talking heads, which is what
we're doing now. So you know a little side by.
Side. Of us just being idiots so you

(37:11):
know like again this was used you can do this with yourself.
This is pretty easy. You just did AO ref of a picture
of me and an O ref of a picture of drew into like a, you know,
stupid caricature image. And then, you know, now we can
run it. And now that you basically.
Have and now our YouTube thumbnails are out of control.

(37:32):
Some of the stuff you sent me isinsane.
It's the game we have to play on.
Dude, guys, OK, so you know, continue to talk about video for
a second. How much you loving the fact
that we got an explore page now with video stuff?
I have an admission. I have an admission of guilt.
I have not looked at it one timeyet.

(37:52):
I I haven't, I haven't really like scrolled through yet, but
this is awesome, man. So, so good.
You know, you got similar, right?
So default you've get you've gotimages.
You had random, hot top day. You could sort this top week
month, you know, images that youlike.
Now you've got this option with video.
There's no hot, but you've got random, you've got top day.

(38:14):
Let me see. OK, top week, top month, and
then you've got ones that you'veliked.
Still don't know how they pull those in there, but regardless,
the other thing is like. Yeah, there we go.
OK. Whatever, whatever.
Is that yours over on the right?No, that was where I got the
idea from. All right, cool.
I was going to say that. Looks that looks very familiar.

(38:36):
Yeah, this one's dope. Does it have the prompts in
there? All right?
So that's the interesting thing,right?
When you when you hit auto prompt it just uses your image
prompt like. As the as the yes.
So the other thing, the other thing that we should note, I
don't even know if we mentioned this, is that there's an the
extend, the extend feature. Yes, and it.

(38:56):
Works really well. You can extend up to four times.
I tried to just keep going todayso you can get 25 seconds worth
of a video and it's super coherent.
There's no jumpiness in between.You know, it's a lot of times
you see with the other video generators when you have to
extend or it's like you extract the last frame and then start
again. It's not a seamless motion.

(39:19):
VO3 does it really well. Not a lot of other ones do it
well, but this one, there's a very seamless pickup from like
here's the end of the video to then it just keeps going right
away. It's super smooth.
It's exactly what it is. So you know, I kind of like 5
seconds, as weird as that soundslike I I think 8 is the perfect
one. But.

(39:40):
You know 5 to me is good if you can extend this.
Well, what did you, what did youtype in there?
Girl walks away from the camera into the burning fire and
catches fire and screams. I've already extended this a few
times. I want to see if it and you know
what like I'm, I'm, I'm also interested in in playing with
this. I'm sure you're probably doing
the same, but you know, I'll, I'll take things that originally

(40:02):
started as a low motion or a high motion and pivot.
And see how that adapts too, right?
So I would recommend like if youare experimenting and trying to
like figure out how this works, like do that.
I think, I don't know if I have any strong observations on that
so far. Like it doesn't throw things
into a loop by any means. So I think that's a that's a

(40:23):
positive, which is really cool to see because I think like you
can in theory, right, like have parts that are sort of like more
even pay slow and then all of a sudden they accelerate or vice
versa, right? Things start really fast and
then all of a sudden you kind oftone it down like that.
Those are those are interesting techniques and it's a very

(40:44):
simple thing to do. So I like that how that kind of
bakes into, you know, they, theyplay well off each other, I
guess is my point. And I'd like to see that
continue. Let me actually let me let me
pull up one because I ran the full like 25 seconds before
before we got on. Let me let me see if this girl
catches fire real quick. I'm still running out.

(41:05):
Yeah, I'm really curious to see if she catches fire here, and I
think I might have one. Here's the other thing.
I timed it today. It was 48 seconds.
It's like, that's insane. It's like, damn, that's how long
it took on for one generation. I'm like, that's again, subtle
winds. That's a win generating AT480P.

(41:28):
You can get it at, you know, I, I don't know if it's a tactical
decision because everyone's like, you know, if, if we get
faster gens, people will generate more.
You know what I mean? Like I.
Don't know if it's tactical, butI like it and I like, I like
being able to rapidly iterate their stuff and just like scrap
and keep going. And having it at 480P allows you

(41:48):
to do that without wasting too much.
Did it? Did you catch on fire?
Yeah, a little bit. Only one of them here.
Which one? This one right here.
All right. But takes a little long to
happen. Let's see.
Feel like it should already happen.

(42:08):
Let's see what happens here. Going back to the observation
thing, when you said that, I found that the prompt is more
coherent on 1st frame than it ison extent.
So the one thing that you're battling with everyone, just so
you know this, this is true across basically all the video
platforms. When you extend or use like a,

(42:30):
you know, if you go and try to make that secondary clip, you're
at the, you're sort of at the Bay of whatever the camera or
the subject is doing. So like if you're, if your
camera is like swinging right and you will like no swing it
back left, a lot of times it's not going to do that.
It's just that's just not the way it's it's like going to keep
going right, because that's the way it's already going and you

(42:52):
extend and you can keep going that way.
So if you feed into it, like if the camera is going right, like
keep it going right, there's things like that where you know
you can't have the camera reallygo up and then like drop like
way down, like it's not going to.
It doesn't work that way when you extend, like there's certain
tools you can do that with, withtext to video a little bit
easier. But with that being said, just

(43:12):
know when you extend. I think that's a really good
point. Yeah.
So if it's like push in and you push all the way in on like
close up on someone's face, but then you extend your like pull
out, sometimes that'll work. That's probably an easier way to
do it then like swinging, you know, with it.
I'll show you an example of whatI'm talking about because
sometimes you just have to roll with whatever the camera's

(43:33):
doing. And that's the easiest way to
get a better generation. If you're text prompting.
If not, if you're just hitting autogen, hey, look, someone took
that. Definitely.
Someone definitely utilized the my girl in a red dress with a
giant animal behind it. Click on that prompt, get it
shot. Yep, that's yeah, that's the one

(43:53):
I shared on on Twitter with the I used a girl in a red dress
with. A giant Oh no shit with a it is.
With a giant rhinoceros. And I'm like, that looks
familiar. Yeah, that's kind of dope.
Sharp Round Top. Oh, that's sick.
Yeah, that's dope. What dope idea I'll.
Wait, go back to that one real quick click on the 1st frame.

(44:17):
No, it's the right the app all right.
So it didn't. So it added that it wasn't in
there to begin with. Right graffiti in red and black
tones. In sticker format.
In sticker format. Interesting.
Good to know that that can be done though.
Didn't even think. About that, I mean that's that's
I think like the value of. Oh, click on that one, that

(44:39):
product photo one. I'm just curious, yeah, to see
how the like the pineapple on the top keeps keeps consistent.
Dude, this is like a, it's like built off like a 3D sort of
mindset here, 'cause those weirdthat those like you see the
pineapple shapes, these are likeweird nerd things that I'm
looking at right now, but the pineapple shapes and the
shadows, they stay consistent. With this whole.

(44:59):
Thing with the broccoli and the kale floating above it, or if
that's cannabis, I don't know what it is.
Yeah. What is that?
But that's like. Something maybe it's maybe it's
kale. Cannabis sounds awful.
Vegan. Yeah, there's some good stuff
here. But like this is this is a
perfect thing too, right? Like new feature, new

(45:21):
capabilities, explore page can unlock some ideas that maybe you
didn't have. Also gives you some Intel on the
types of prompt. You know that achieved it,
right? So like just like that perfect
example is this right? It's like don't know that I
would have thought of that, you know, and probably wouldn't have
thought of it for a long time, but that's super dope.

(45:41):
Love that. I did that a long time ago in
runway like sketch where I did like doing like sketch to
basically because I was using final frame like last frame only
and just having like the sketch as the end.
So trying to like animate it with the hand and that worked
which is cool, but like there's.Look at this shit.
This feels like this feels like some you shit right here.

(46:03):
With one. This fucking chimp.
Look at them. Oh hell yeah, that's me.
That's amazing. That's amazing.
Let me show you the Let me show.You the Yeah, Show me what?
Yeah, show me what you. Got this one.
This was pretty impressive to me.
I was just screwing around with this before we got on.

(46:23):
Let's see if this I don't know which one is the right one, but
I'm I'm hoping it's one of these, but like if we started
here, right, just so everyone can see the initial frame or
maybe not, but that's the initial frame, right?
Crazy. There's a lot of motion in it.
You see what I'm talking about with like the motion blur to
begin with and like everything that you can see that it's

(46:44):
already moving to the right. I don't have to prompt for it.
I know that's just going to pickup and run with it.
So like it takes it and then it goes and this is like the first
clip, right? And then we go into the second
clip where it's like zooms in, curves around and then like we
swing around front and you can see the camera motion or the the

(47:05):
camera shadow here somewhere there it is over here on the
left. We just keep going right.
So this is again, this is prettydamn good for extend.
You would never know where the clips extended.
They just sort of bleed into each other, which is what you
want. They, they do bleed in really
well too, right, 'cause like even when I was going back and

(47:25):
like trying to pick, you know, first you gotta find the one
that you like and then it's like, OK, which one am I gonna,
you know, extend? And then, you know, you get the
extensions and then, you know, you compare those, right?
But like, that was what I noticed, you know, in trying to
like analyze each one of those, you know, I would click in and I
would Click to that point right before because there's a break

(47:48):
that it shows you. And I don't know if you can see
because you've got like that that share screen button right
on your thing, but. What happened here?
What? Well, you can go back to you can
go back to showing what you had,but I was the point I was trying
to make is there's it shows you the break, right, like when you
go into and so I was skipping toright before that and as it

(48:12):
would go into each one, it was so smooth and subtle, right,
because like you're like, Oh, I like I was expecting something
to change instantly right when it started, wouldn't even know
right. So I think that is a really,
really interesting and good point too.
It's like, damn, that's kind of dope.
Really bleeds in well. Yeah, this one, I think this one

(48:33):
was impressive. Just that most time you have a
hard time getting turns with cars, as weird as that sounds,
right? Like getting a turn is an odd
thing. VO3 does it well, Kling can do
it now. Well, but like having a sharp,
like 90° turn, that wasn't something that was really easy,
right? Like this one to me really kind
of like you guys again, just nail.

(48:55):
It that's a tough one. Stuff right?
Like some of these motorcycle shots too.
And this is again, I'm talking about adding motion to your
image, having that motion blur. It just like makes a big
difference with this. Like some of this stuff looks
super real. And you know, I'm sure there's
they have a lot of motorcycle data, you know, like some of
these, I don't know if it's thisone, but like even the curving

(49:18):
of the camera like with that, like these are complex.
If that's not easy, you know this isn't something that every
image generate or any. Lot of variables.
A lot of variables. And keeping consistent with the
colors and keeping everything. That's the other thing we should
mention here. There is no color loss, zero

(49:38):
color loss from one thing to thenext, like one from image to to
video. Like I was totally shocked that
this didn't lose color like evenon the softness on the on the
earrings and stuff like that, like this guy, right?
Like it keeps the style perfectly and then continues to
animate with it. Like even all these little micro

(49:59):
details here might not be perfectly, you know, resolute,
but I was really like, these arelittle things like that soft
blurriness on the earrings killer.
Have you have you tested images outside of the journey yet?
I have not. I haven't either.
I have so many. I know I haven't either.
I I asked because I'm wondering if that's if that stays true

(50:22):
with your point around the coloroutside of mid journey images,
just in terms of like how it picks those things up.
But like this insane, you know like this, this color should
should not work like these. These are really.
I mean it's that is extreme. And I was like, this is so cool
how that looks. This one was the original one

(50:43):
that I was like, all right, I can take something that makes no
sense and it'll work like it is so, so extreme from a color
standpoint. And I was like, that's it.
That's the one that that's the one that's specific video.
I was like, yeah, we're we're going.
Don't ask me why people probablyis the dumbest thing I've ever

(51:05):
seen. Like that's I'm just like that
color is so extreme. I mean, dude, that's what.
But I think the point we're trying to make though is in
theory it shouldn't work. We haven't seen that type of
stuff work. No.
Yeah, and here's, you know, and.You'll see not that, not that
I'm sorry for cutting you off onthat one.
Yeah, you're good. But we'll do that again to

(51:27):
another to dropping back to another podcast that we talked
about. There is mid journeys brightness
factor like you see this with a lot of other image generate or
videos. They they get dark because it's
too much power to render detail V7 super bright because it can
handle the detail. Now the video generator can
handle the detail too. So that's I just wanted to throw

(51:50):
that out there that we're just we're hitting on all cylinders
here from from previous episodes.
If you guys haven't listened. Do we really are?
Yeah. Yeah.
Hey, there's never been a bettertime to go back.
We see that every episode. Look at this one.
This one's pretty dope. Like this.
Love the just. Yeah, everything about this one.
Did it get hunt on both sides ofthe car?

(52:11):
It did. Nice.
And all it had was burnt orange.Hunt logo didn't even put it in
quotes, but it this is the image.
So yeah, that that recognition, Right?
Yeah. Hmm.
Actually take that back, it was wrong 'cause if it was the other

(52:31):
way, like if you go back to the image it says hunt left to right
and then here it says hunt left to right.
So technically if it was the same, it would be see how H is
at the end right? Like not the not the beginning
of the word. Do you see what I'm saying or
no? Kind of.
Like right here, H is the first letter on the other side, H is

(52:54):
the last letter. So it's it, it makes sense.
It's still like impressive that it did that, but.
Oh yeah, I mean, well, that's but, but that's that's how you
would display it though, right? You wouldn't want them both to
be facing the same way. Correct, but I'm so.
Oh, you're just saying like, dude, the fact that I picked
that up. It just picked that up, yeah.

(53:16):
That's yeah, dude, that's fuck, that's it.
Yeah, I know. That's awesome.
I mean, and and there's no variation, right?
There's no variation in those hunts because, you know, even
something as small as that couldruin the image or the the video
And and now, like, dude, I mean that there's just a little
scene, all the colors popping, that little neon.
I mean, that's still. Fresh the rim, even the rim

(53:36):
color was orange on the left side, you know, it had like the
little orange trim over the black rim and the same on the
other side like it's, it's things that you want like that
'cause that's that stuff that wouldn't have worked in the past
in a lot of other, you know, generators.
Should we also, you know, throw in should we talk?
Should we talk SRAF update? I mean like definitely

(54:01):
interested, definitely rejuvenated.
I think like my observation and like running Ah fuck man, I've
run so much shit over the last week.
This has probably been the most I've run in a long, long time.
But. Those fast hours dude, you get

(54:23):
so many. Yeah.
What I'm noticing though is those these S refs do look more
pronounced. I don't know if that's the right
word, but they they like whenever I'm running S ref
random they they look the variance in between each ones
are much different. The styles almost seem stronger

(54:44):
in some way. I don't really know how to
explain this, but there's something different there and.
I got some good ones. Finally.
There was like a run where I hadlike eight in a row and I was
like, oh, OK, never really like eight in a row, but what's the
Yeah. I know, right?
Time out so you go dribble.com Iknow is one of your go to's.

(55:06):
Yeah. What's the other some of the
other testing tokens you like toutilize other than?
I know you use some emojis too, things like that.
Yeah. OK.
So I, I mean, there are a couplethat that I go to over and over
again, and then there are a couple that I mix up.
So let's go through. Let me see if I can find like a

(55:28):
fresh batch where I've like run.These are after I've upscaled
them. Jesus Christ.
OK, so dribbledribble.com, I love I always run dribble.com
and I always love dribble.com character, love to see kind of

(55:52):
like the character aspect of it.And then dribble depending on
like the S ref, we'll pull in either a character or it'll pull
in like just sort of like a coollittle art scene or something,
whatever it is. So I always do those.
Let me find like, let me find like an actual like dope.
B hands what I did. For I've done I've done B hands

(56:12):
before. Behance always gives me a
Porsche. I don't know what it is.
It's always Porsches. You know, so so like this is
after dribble.com, dribble.com character.
I always like an album cover. I always do album cover.
Sometimes I'll do movie posters.Another good one after that.

(56:33):
I really like makes it up. And I think like what I've been
doing a lot of lately is I'll I'll just put in songs.
I'll go through my Spotify and put in song titles and like like
on that last that SRAF I was showing with the videos, like I
did like a whole ACDC run where I was doing like Highway to
Hell, shoot to Thrill, Thunderstruck, you know, stuff

(56:56):
like that. And like song titles can give
you some good stuff, you know. So like I was going through and
I did like dreams I'll never seeFlirting with disaster.
Those are those are songs from like seventies, 80s and then I
was doing like some Stoicism. So I was doing like memento
Mori, Amorphati Stoicism. I like doing Nike ad creative

(57:19):
from time to time too, because Nike usually comes out pretty
good and it's always interestingto see how an S ref adapts to
that. Yeah, the Greek mythology here,
but run with. Your profile on.
I do, I do, I run with the profile on and then I will Also,
one thing I really was liking isI went back to member core, wave

(57:46):
and punk and I just started running those one worders like
weird core, dream core, dystopian core, like whatever
the fuck it is. And I just went through my whole
list of like core and wave and punk and I could throw those in.
And so then what I'll do is I'lldo basically that.
Like here's how I build it out. Just like I'm going to do this,

(58:09):
I'm going to do this, I'm going to do album cover, I'm going to
do Morfati, Memento Mori, Weird core, dreamcore, Rainbow core,

(58:31):
what I mean, whatever it is, right?
So then I'll usually run like after I find the S refs from the
test, right, that I'll run with the skull in like R40 or
whatever it is. I like hide all the ones I don't
like. Then I'll go back the ones that
I do like, I'll, you know, I'll kind of like cull that list
again. I'm like, oh, which are the ones
that really stick out. And then I'll run this.

(58:52):
I'll run like something where I'm running like probably 10 or
12 different prompts. So I would go longer than this.
Typically. I usually run a R45 and then now
what I'm doing now with Exp is I'll run this at zero and then
I'll also run with 15. Damn.
And that's fun. So so then you get like sort of
like that aspect of like as is. And then you also get this

(59:15):
aspect of experiential. But it like I noticed if you go
too high on the experiential, itstarts to deviate right from the
S ref code. Like it starts to kind of like
not completely, I have the colors, but it'll but it'll kind
of, yeah, but it'll kind of liketosses aside.
So like 15 or 10, I would recommend if you do it that way.

(59:38):
And then I'll just usually run the fuck out of those, you know
what I mean? And then out of that list, then
I'll just go through and I'll say, OK, I'll look at them first
and I'll say, is this even worthsharing?
And I'm like, I'm looking at this and I'm like, probably I
don't really care about that. So I'm just going to skip that
one, OK. You know, then something like
this, like, OK, there's some like sick shit here.
So I'll go through, upscale the ones I like, then I'll just

(01:00:00):
consolidate those into a group. And then that's usually when
I'll, you know, pump out one of those posts where I've got like,
the fucking. 22. 22 fucking styles, right?
And then how do you like 22 of them so so?
Picky. Yeah, I like, I always try to go
with like the five good. Ones, you know, like I feel like

(01:00:23):
I never get stuff that looks like that.
And it's probably because my, it's probably because my testing
look, my testing doesn't look that or did testing.
I just, I go, I and I also go through a lot of these.
Dude, I go through so many of these.
You mean because you'll, you'll look at some and you're like,
oh, I like that one. But then like when you get down
to it and you're trying to decide which ones you're going

(01:00:44):
to run with, like those permutations and shit, you're
like, yeah, it's not really thatcool.
So that's when you kind of get to the good stuff.
And so it's, it's a whole fucking process.
I wish I could say it's really quick, but it takes me a long
time to do because I first I gotto identify a bunch of good ones
and then I got to expect that like half those I probably won't
end up running and I won't like.And then you got to run all the

(01:01:04):
permutations and go through and like pick out of that bunch.
Like did I run the right prompts?
Do I like the results I got or not, you know, and then compile
them. So I mean, it's kind of a just.
Putting that PDF together. It's, it is fun though, like I,
I, I definitely do kind of enjoyit.
It's it's kind of cool, but I, you know, this new S ref system,

(01:01:24):
in case you guys don't know, this is where I think it's a
little bit confusing and it's going to be hard for some people
is because the the new S ref system right broke the legacy
system. Meaning if you were to use this
code and not attach dash dash SVspace 4, you're going to get

(01:01:49):
something totally different because because now with this
new system, the codes are related to a different style.
And there was like, it was such a weird, you know, cut off.
So like the cut off. The only cut off I can think of
my mind is the date. It's like, well, it happened on
616, but like, what the fuck does that mean?
How am I going to know? Is this a legacy code or not

(01:02:12):
right? So I think that's like maybe a
confusing thing that, you know, could use a little bit better
sorting and. I totally missed that something.
You know, but but that's but that's that's the thing, right.
And that's where I was like, I was already pulling those 22 and
then I'm like, I see the new S Rev and I'm like fuck, because

(01:02:32):
not going to explain, you know, these are codes, but make sure
you plug in the SV 4, otherwise you're going to get something
fucking totally different. So I don't know they, they, they
do need to figure something out with that specifically.
So it's not crazy confusing. But do you never run?
Can we run? Can we do?
Can we do 1 real quick? Let's do one.

(01:02:53):
Let's find just find a good code.
I'm curious if you. Yeah, let's.
Yeah, I just I just ran AR-40 let's.
Do just find one that we like? I just want to do permutations
SV1234. Let's see if it works.
I'm just. Curious because it people forget
that you can use SV1234. I do it.
I remember every once in a whileand sometimes those SSV 3 and SV

(01:03:15):
ones are bangers. Like, you see, like, none of
these are like, really dope. You know, to me so far, this
one's kind of cool. This one's kind of cool, kind of
no, no, no, no, no, no, no, no, you know, like interesting.

(01:03:36):
Not sure, right. Like these are, these are the
ones I'd probably like hold onto, but I probably wouldn't
run like kind of interesting, but not like one of those things
where you're like, oh, I gotta run this and see.
So that was that was interesting.
How did you like that one? I like the skull teeth.
I'm gonna let's run a fresh 40. We got hours of burn here.

(01:03:56):
Let's go. Let's run a fresh 40.
Let's do, I don't know if it's just me on this either.
This feels, maybe I'm in my own head on this, but when I do an
R10 and I run that four times versus an R40I feel like I get

(01:04:16):
better things during the R10 than the 40I.
Kind of feel the same way, I don't think is that.
Fucked up. No, I think it's real.
I think it's also 'cause you cansee them in a more digestible
like when it's 40I. Just want to like get the.
Bottom. Brow like give me like something
like this, something crazy. This looks I can fuck with that.

(01:04:37):
So. So hit that one with the with
the crazy neon colors. OK.
Use that prompt. OK.
And then I've definitely hit thehigh motion instead of use
prompt like a million times already like when I wasn't
expecting to. Right.
And I was just, I had it took mea second took.
Muscle memory. If you do permutations on dash,

(01:04:57):
dash SV and then do 1234, let's just see how.
Different do you, do you? They haven't said this, but I
mean, is there an SV6 or whatever the last number is now
that we've got this new system, I mean.
Is there? I'm confused.
Let's run 5. All right, so let's run this.

(01:05:21):
We'll run this first. All right, so why is it saying
SV6? Can only be used with SV4.
Got it. SV6 for version 7.
Wait, so try it. Wait, what?

(01:05:42):
I'm confused. I'm so confused.
With this now, yeah, I'm 2, so 123, so it was saying 4, but I
think, OK, let's well first let's do this.
Can we do this? No.
OK, So what it's saying is I think 123 are those they either

(01:06:07):
don't work or they have to be used with V like AV6 model I
think so I don't know. Do you still want to try that?
Yeah, try it. OK, so let's let's just see.
OK, so let's try 4:00 and 6:00. Should we try 5?
Like what is there fucking 5? What did it run?

(01:06:31):
It ran 6 and it ran four. There is No 5, or at least 5
doesn't. Yeah, at least 5 doesn't work if
there is one. What's the difference between 6
and? Let's see.
OK. Whoa.
All right. So four and six way different.
So this is so then this is it right?
This SV6 is for the new codes. Huh.

(01:06:55):
OK, interesting. SV6 is for the new codes.
I didn't either till till just now so.
This is yeah. Can we go?
Can we do old S ref codes if with SV6?
Do you have? One code.
Well, you can, but it's not going to be the same style.
Huh. You would have to use four.
I see. Which is why that that that was

(01:07:15):
why I was like that 22 is like, man, I've got some good codes
here, but now I have to like go the extra mile.
They explain like these aren't going to work unless you do the
dash dash SV4, right? Because if you just because SV6
now is the default, right? So if you just plug that in and
you don't put SV, it's going to default to SV6.
All right, I didn't know that. But like, let's let's take what?

(01:07:39):
But but let's take this code nowand let's run like just for the
sake of it. Let's just since we were talking
about it, let's run like an experiment here of maybe like a
typical thing I would do. Let's do movie post.
Maybe let's do a movie poster, movie poster.
Let's do cosmic dreams. Feels like a good one.

(01:08:03):
Let's do she like a. 3D shape orsomething like that I.
Feel like, I feel like, yeah, I used to do that, yeah. 3D shape,
maybe 3D shape melting hedonism is another kind of cool one.
Let's do like some of these coreones.
Weird core. Let's do like dream core myth.

(01:08:25):
Punk myth, Punk I. Remember that one from back
Carpet Punk? Carpet punk.
I remember that one. That's.
The name of the episode. Carpet punk.
Yeah, there you go. Memento Mori and let's do.
Wabi sabi. Wabi Sabi and let's do a Nike ad
creative and then what we'll we'll do is we'll run that AR-45

(01:08:51):
and then let's do the let's do the AXP, let's do a zero, let's
do a 15 and. Bang on.
Boom. And so and so the shortcut of
that too, like I don't know how other people are doing this, but
if you are like mining, then then I'll copy this, right?

(01:09:11):
I'll copy this part. And so then once I've gone
through and identified the ones that I want to run, right, I
just paste that back in and thenall I got to do is click the the
code and then run it again. So let me make sure.
There's a science to this. There is, I'm just going to run
turbo. It's weird because you don't you

(01:09:32):
don't really go like I I try to find my my one test term that I
like to use a lot is samurai, because I know it's going to get
a lot of. Detail.
Yeah, that would have been a good one.
Samurai's always like, it alwaysgives me detail, so I can see if
it's going to be minimal or if it's going to be deep or it's
going to be like maximum maximalist or whatever.
But all right, we got some, we got some interesting stuff here.

(01:09:57):
Fuck yeah, and you'll see like you'll see like these are
different too. Like the reason I like dribble
too is because it it tends to bemore of like the the
illustrative 3D ish kind of style And these other ones are a
little bit more sometimes a little bit more photorealism
based depending on the SRF, but.It's always interesting you got

(01:10:23):
to kind of work with the SRF, what it's giving you because
this one wants to be close up and it you see.
There you go. See so that, so like that's the
stuff I'm like the fact that I got 2, like what I take away
from this. I've got 2 skulls here, 2/3
right right here. OK, so I've got 2 skulls here.

(01:10:44):
I didn't prompt for a skull there, right?
So that's interesting. Also to your point, a lot of
close up stuff, half these are close up, right?
So that's telling me something to your point.
Now we're seeing all these facesand they all kind of have like
this tilt to them. So you know, like that's baked
in to the SRAF, right? And then especially here, I
mean, this movie poster thing, Ican't tell you how basic this is

(01:11:09):
compared to most S refs. Usually like the movie poster
thing, you get some really interesting things.
Same with the album cover. This is so like this is actually
a probably not a great S ref. I mean, the colors are awesome,
but what I'm getting back here is not all that interesting.
Now here's the here's the thing.Try see if you go back to the OR

(01:11:33):
just try like movie poster but run it with like 2/1 to see what
happens at like 2-1 aspect ratioinstead of four or five.
Sometimes I find the S reps change like I always run them in
four or five and test them 'cause I just want like the to
be in a nice comfortable grid across.
Sometimes, like changing the aspect ratio totally changes the

(01:11:54):
aesthetic. I don't think.
It's gonna change it with this one that much but.
Yeah, no, I, I like, I like where your head's at.
Let's run that. But I think what we should do
too, we should find a, we shouldfind a better one because I do
want to show like the variability that I typically get
back with these, like this is interesting.
I would run this for sure. Interesting that one's going to.

(01:12:19):
Be a good one, yeah? You know you just like which
ones. Are going to be.
Good, that's what I'm saying. And you know, and that's that's
what the hard part is because like you get kind of get
distracted by these other ones and at the end of the day, it's
like, what are the ones that really fucking pop out?
Don't even waste your time with the other ones.
So like, I think we should run, I think we should run this one.

(01:12:42):
I feel like this would be a really good one to run.
So I copied, you know, I had that copied paste.
Now we're just going to add this.
Boom, let's run that while we'rewaiting.
Now let's go check out what you said with the movie poster
aspect ratio and what changed with that.
Nothing changed. Yeah, So I mean, so I mean, it's
a, it's kind of a shame, right, Because these colors are sick.

(01:13:04):
I mean this is acid trip type stuff.
Really cool. I use this one on like a low
SSW. Like, well, OK, that's a great
point. That's OK.
So that's also a great point, guys.
Great fucking point, Rory, Because when I'm doing this, I'm
not I'm really not changing the weight default's 100.

(01:13:25):
But this, this maybe is a great example of you like the colors.
These colors are so probably strong.
It'd be interesting to lower that maybe down to like a 50 or
60 and see what happens then too.
You know, like do you do you break out of that?
And I think maybe what I would try is let's go to the one of
the ones where we wouldn't expect to see just faces like so

(01:13:45):
this movie poster again, let's go back to this.
Let's take this and then now let's run Southwest 50 and maybe
let's do like a 40 and let's do like a 70 and see what comes
back. And then we'll and then we'll
dive into that other one here. I just got AI just got a 10%

(01:14:12):
notice on my on my my battery power.
So I might I might have to dip for two seconds.
This guy. Totally free, totally forgot
that I did not have my computer.That's right.
That's right. So, I mean, OK, so Long story
short, this is showing like evenwith lower weight, we're getting
colors, we're still getting themclose.

(01:14:33):
Yeah. Kind of a bummer.
Kind of a bummer. Kind of a bummer.
It's really good one. This was the other one.
This was the other one we ran. I think this is like, this is
like a typical example, right? Like you're going to get some
interesting things here. This is where like adding the XP
is nice. You can also rerun these.
So, you know, sometimes if I really like kind of where it's
going, but I don't love any of these images, I'll reroll those.

(01:14:56):
The characters are always interesting.
There's usually a good one in there.
Album cover. I would say these are kind of
weak for an album cover. Usually I get some better stuff
than that movie poster. Like there's some, I mean,
there's some good stuff in here.It's not bad.
It wants to. Be it wants to be landscape
right? Like it wants to.
Show it does a little bit yeah. Hedonism, 3D shape melting now

(01:15:19):
like, you know, I'm getting somekind of cool stuff there.
Weird core. Weird Core is an interesting
wild card dream core. Myth punk?
Carpet Punk. Do you?
You get so many more illustratedstyles than I do, and I feel
like I always get like these these random.

(01:15:39):
I get some really weird photorealistic stuff.
Even with this code though, you think?
No, not with this code, no. No, just like in Jet when I run
As for referendum. At all.
Oh, OK, I see, I see. But yeah, man, some.
Of these, they're described and see what you get.

(01:15:59):
Like I always try to like, it's like those neon ones.
I just pick. Pick me out one.
Like the yeah, like that with the girl with the purple face,
like close up, like what's it gonna say?
Like, what's it gonna, how's it gonna describe that 'cause
sometimes it's an easy way to sort of take some things you
like about, you know, your SRF codes and sort of.

(01:16:20):
Smart man. Smart, Yeah.
So like hold on, just just run all real quick.
I'm just curious if anything even comes out.
Yeah. Like close because sometimes.
You run, see, there's that's that's why I love this fucking
tool. See, like I, I I wouldn't even
been thinking about describe at this point.

(01:16:43):
Super dope idea though. Because sometimes like when I
get that, I'm like, I don't evenknow what that art style is or
how it's like. 'Cause I.
Might like some of it, not all of it or the color like
whatever. What did it say for the colors?
You know, I like that color scheme.
I can go look up the hex codes, but I.
Don't know this one. Yeah, I was like one of them.
Like one of them was really, really.

(01:17:03):
I think it was maybe this one, but it was just like electric
neon purple. Yeah.
So they don't really get it. See, they they don't even they
don't get that close with the scribe, but.
Not without the S for F, yeah. Certain things to pick up.
I always whenever I see one that's like so random that I
don't know what it is. I'm just like let's see what mid

(01:17:25):
journey thinks of it. What does it think it is because
I don't know how to describe. It I don't think they call out
the fact that she's got a purpleface.
No. Or whatever the color of her
skin is, right? They they should, but the color
is not as good as it is in the Sref code, you know?
Yes, ref. Damn, I wish, I mean like this.
This goes not bad. This goes not bad.

(01:17:46):
I just wish we would have, I wish we would have had a banger
for for the episode's sake, but I think you're.
Live, this is what happens. This is this is it, but I think
like this is this is really good.
I'm I'm interested to see too. We didn't really talk about
this. I know your batteries on low, so
we'll kind of wrap this baby up,but like how this effects mood
boards too. I want to revisit that because

(01:18:07):
that was also a supposed to be apart of this, right?
Mood boards supposed to have improved.
I think they have personally, without even them saying,
without even knowing that remember we were saying, I think
we're saying this again. I feel like I'm a broken record
here talking about the last episode or the other episode of
like these. They seem to work better as of

(01:18:30):
recent, like more consistent, less glitchiness, less softness.
I'm trying to think of like maybe, maybe one I didn't love
to, but to try, but I don't know.
Yeah, these are these are worth going back to.
I'd love to test this out. I haven't.
I haven't had any. These are old.
Really. Yeah.
What was the what was the character one with all those

(01:18:51):
little ones, these guys avatars too?
I found I found like these cool little guys.
I think this was more of a test.I don't, I don't, I haven't
really used this, but you know, just to see if I could like
generate more of this style of character.
I just thought these were kind of cool.
They kind of felt felt a little like NFT ish, you know?

(01:19:12):
Yeah, The other thing have you noticed with style reference,
the one thing I did, I was running it this week and knew,
noticed that it wasn't as they said.
I think, I think I read to be quite candid everyone, I totally
missed the SRF update because I got so excited about video.
Didn't even didn't even know theSRF thing happened until I saw a

(01:19:32):
true post about it. And I was like, OK, but there's
no subject leaks. That was one things they called
out, which we were always, we were always saying, right.
It's like yeah, the subject leaks in with the SRAF it leaks
into. The yes, but they got.
I've never heard them ever talk about that.
No, but then then they just updated it and said that we're

(01:19:54):
going to fix it. Then this one's out there.
And I've noticed it because likeI I was using like I was doing a
testing it. I was doing like a Nike took a
bright white, just plain all white Nike sneaker.
And then I used a jungle photo as a, you know, as a S ref to
see what would happen. And it didn't pull any of the
jungle element in which I found interesting because that's not

(01:20:16):
normally how it would work. It would bring something in of
the jungle. Yeah, you'd have to really dial
the weight, yeah. But I just took the colors.
So it just really took like the like it had like some, you know,
like the jungle had like some like, you know, like haze or fog
in it. And then it had like really
sharp green and really dark black.
So it brought all of those elements in, but not the.

(01:20:39):
I'll see if I can find it beforewe bounce out of here.
But it was just an interesting one that I noticed that would
normally that would leak some some jungle, you know, some
jungle stuff in. Yeah, I was surprised that it
didn't. Yeah, I, I, I haven't yet tried
that part from a third party style reference yet because all

(01:21:00):
I've been doing is with the, with the codes.
You know what? People are still confused by
that. People to this day are still
confused. That style reference, there's 22
versions, right? There's mid journey style codes
that you can unlock or use. And then there's just any other
image on the Internet that has colors that you can bring in and

(01:21:25):
use, you know, to guide the style or the color of the
aesthetic of your image. But I haven't tried I, I, you
know, I think that's probably something that we could try for
next episode. Is, is how that's now working,
that subject leakage, you know, diving into that and I'm curious
to see how that's how that's working.
I'll. Show you what I'm talking about
real quick here. Yeah, so this was, this was

(01:21:48):
interesting to me 'cause typically I would, I would
really expect this to come through.
This was the reference image, right?
I expect some of that to come through, but it just kind of
came through with the green, theblack and the smoke.
Right. So that was interesting.
Because I was running. Then I ran an image.

(01:22:09):
Dude, I like those. I love those colors.
Yeah, it was really cool. I was just like, I wanted to
play with. So this again just didn't bring
any of the structure over. It just took sort of like the
just taking like the vibe, right?
It's not that, you know, these aren't like my favorite shots of
all time. I was just trying to test this
with this one jungle shot because I was like, you know,

(01:22:30):
because then you can use. But that's a but that's a really
good test though, because you, you've got a very like very
simple isolated subject here. But your, your style reference
has all these leaves, right? Like it's not just like this
green color in the, I mean, it'sgot it's this whole object
texture thing, right? And it's basically just taking
that color, which is super interesting.

(01:22:51):
So I think this kind of is proving that point of the
subject. I mean, that's I, I really want
to play around with that. Because then if you use, you
know, was I think this was a refmaybe if I'm not, I'm not
mistaken. This was Now I use when I see
here in a studio, I can't remember which I was trying to
like do it through like 4 different ways to see like, oh,

(01:23:13):
does image prompt do it? You know this one odd.
So this one I used O ref with the sneaker and then this as an
image prompt background as an image prompt.
Then it worked brought in no problem, but I was interested
with the with the style reference 'cause it was giving
me like a lot of variance like it wasn't it wasn't consistent.
I was trying to sort of figure out what the consistent sort of

(01:23:36):
look was. There wasn't much.
So you know, I even here is likestyle weight 900.
I tried to dial it up to see if it would bring in the leaves
didn't bring in the leaves. It brought in some green in the
grass, but. One other one other question I
want to ask next office hours isclick on any one of those images
again. Oh shit, you just hold on.
There we go. Hold on.

(01:23:57):
We're going back, OK. One second, I don't want to
crash your computer, but I, I'm,I, I am curious and I would like
some, some goddamn transparency around this.
OK, click into one of the OK, sohelp us improve V7.
I like this image. I don't like this image.
I'm neutral in this image. Can this factor into

(01:24:18):
personalization? Does it, can it please?
You know what I mean? Like this feels like a great
opportunity. I'm, I'm already generating a
bunch of images. I don't have to like it, but
you're asking for the feedback. So how, you know, I understand
that it's applying to the model as a whole, but can't you can't
that also be applied to me, my own personalization, you know,

(01:24:40):
because, you know, we've, we've talked about it.
People have talked about it aired some grievances.
They, they maybe don't like their personalization now with
V7 or whatever it is. I'm not alone.
Take a call, fuck all y'all, Butyou know what I mean?
Like they, there's something there changed.
I, I just think like that's a great opportunity to to, to
impact personalization too, because you've got got all those

(01:25:02):
images right there. You're already clicking into
them. I mean it'd be a great way to
just like I don't have to go to a whole another tab just to rank
images and I I know those are random images, but can I apply
that to my own images that I've created?
It'd be nice, be nice because, you know, whatever.
I haven't ranked images nearly as much as I did with.
These I haven't either. I haven't either.
That's it. I mean, dude, we got I have 3%

(01:25:25):
left. Sorry everyone.
It's a good. It's like a natural cut off for.
Us, bro, this is a natural cut off because we we could go, we
could go for a while. This is mid journey fast hour.
You know, we already push it. We always go a little bit over
the hour. We're going, you know, now we're
an hour and a half. So anyway, I think this is a
good place to wrap. We still, I think have some
things that we could roll into to next week to to cover to if

(01:25:48):
we wanted to. I think, you know, I'm just
excited. This is the best I've this is
the most excited. I've been about mid journey in
probably a year. Yeah, ish.
I mean the video stuff and you know what I loved Rory.
It wasn't this long dragged out thing like yes, they did.
They have been talking about video for a while, but it wasn't

(01:26:08):
like one of those things like V7where I was like, OK, we're
getting close, 11 week away, twoweeks away, whatever it is.
And then you got a set back and you know, like this just kind of
hit. It was just like, oh, it's
fucking on, you know? I don't know how.
I don't know how it went from like V7 falling behind like 8
months to then we did video right?

(01:26:31):
Right. Like I find it crazy that I know
it's a priority for them, but I still feel like it's a side
project and like their side project just like awesome.
You know, like I use runway for images now and I use mid.
I'm going to use mid journey forvideo.
Like what? Like what world are we in?

(01:26:52):
So, so odd, But you know, this is a good job, good job on the
team for getting this out. They said end of June they
delivered. You guys yeah you guys crushed
it, you guys I mean, if you listen to this, maybe you do,
but you probably don't listen tothe whole thing if you do.
I don't know. But hey, I think really

(01:27:12):
outstanding job. I think the sentiment has been
echoed everywhere. I've seen not many people.
I I really haven't seen any slander about it.
I think people have been very realistic about what to expect
from AV1 version of this and it looks damn good.
I mean, it's, it's really promising and it's exciting
times over here, man, Very exciting times.

(01:27:33):
What's we got a lot? We got a lot going on this one.
We're going to come back probably next week, talk about
it. Maybe we'll bring some guests
on, maybe we'll do something else.
Who knows, but we don't know. We don't know until the day we
do it. So appreciate you all for
hanging with us if you haven't already.
And if you if you wait around tothis part of the podcast every
single time, like and subscribe,God damn it.

(01:27:54):
But you know, hopefully YouTube doesn't take me for that, but
we'll be back next week doing more stuff.
Through just. Sir.
Rory's beard will have grown a couple inches by then.
I had to, dude. I was.
Looking to be back. You're looking clean shaven my
friend. Look at the look at the last
week I was, I was like a homeless person.
So we're we're back now. We're back.

All Episodes

Episode Transcript

Popular Podcasts

On Purpose with Jay Shetty

Ruthie's Table 4

The Joe Rogan Experience

.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;}Midjourney Video is HERE—Nerds React + New SREF System Chop-Up

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;}On Purpose with Jay Shetty

Ruthie's Table 4

The Joe Rogan Experience

All Episodes

Midjourney Video is HERE—Nerds React + New SREF System Chop-Up

On Purpose with Jay Shetty