Author Archives: eric susch

Can AI draw a Red Ring of Light?

Leave a reply

Recently I was experimenting with the Midjourney AI art engine.  I saw an image in my mind of a robot backlit by a red ring-light.  I typed it up as a prompt:

An intensely bright thin red ring light in the distance, a woman robot in silhouette, on an abstract shiny metal plate surface, hyper realistic, cinematic, dense atmosphere, intense, dramatic, hyper detailed, –ar 2:1 –v 5

I expected to get something like the image above.  That’s not what happened.  For the next hour I tried to get Midjourney to build something even close to what I envisioned. I typed and re-typed the prompt, changing the way I described the image.  Most of the time I couldn’t even get a red light ring.Midjourney kept trying to make a “sun” with a red sky.  There are round portal structures, some even reflecting red light, but almost none of them light up.  The light’s coming from somewhere else.

What I asked for was simple.  Why is this so hard?

I’m guessing it has to do with the data set the AI was trained on.  I bet there aren’t that many images of red light rings in there, maybe none at all.

One of the things that frustrates me about AI art is the way most things turn out looking generic, like everything you’ve seen a million times before.  This makes sense of course, because that’s how it works.  It studies what everything looks like and then create from that.  It’s almost a creation by consensus.  An unusual Red Ring isn’t part of the equation.  I could probably eventually get to what I wanted if I kept trying and perhaps made the prompts much longer describing every detail.  Maybe.

Or I could do what I did and create what I saw in my mind with CGI.

Has this put me off AI art?  No.  Every tool is good at what it’s good at, and it’s not at what it’s not.  I was looking for the edge of what this new tool could do (because that’s where the art is) and I found it.  There’s nothing really interesting right here but there’s a lot more to discover…

Robotic Romance – A Colossal Story of Forbidden Affection

Leave a reply

This is another image where I tried to get something in the style of a 1930s SciFi pulp magazine cover.  It looks like the 30s especially with the orange background, but I think the robot looks more 70s.  I like it anyway…

#Art I made with #Midjourney #AI

God is a Machine

Leave a reply

This picture is the first image in a two part series.  The second image Deus Est Machina (which is the same title in Latin) was posted previously.

Deformed hands and tangled fingers have become an iconic symbol of AI art.  The art machine knows what things look like (most of the time) but it doesn’t know what they are.  It starts making a girl with braided hair then somewhere along the way… does it change it’s mind?  …or does it never really know what it’s trying to make?  The result is almost an optical illusion.  It looks correct at first glance but on closer inspection something isn’t quite right.

#Art I made with #Midjourney #AI

 

We Are the Dreamers of the Dream

Leave a reply

Building the Metaverse to match the real world.

I made this CGI image about a year ago when the Metaverse was the shiny new tech thing.  Most people probably won’t get what it’s about so I’ll explain it, even though David Lynch would probably scold me for doing that.

The grey and chrome sphere are tools that special effects artists use to match 3D computer graphics to real world photography.  If you are shooting a film for example, and part of the scene will be CGI, you shoot a few extra feet of the environment with someone holding a grey and chrome sphere.  The chrome sphere reflects the entire environment and that reflected image can be “unwrapped” and placed as a dome over the CGI so the same light and colors shine on the computer generated elements as in the real scene.  (The chrome ball is actually an old fashioned “poor man’s” way of doing this.  There are 360 degree cameras now that can actually just take a picture of the entire environment right on the set.)

The grey sphere shows the quality of light shining on a specific place in the shot.

This image is about building a computer generated Metaverse that people can walk around in, just like real life.  It’s the dream of constructing a Metaverse as well as the Metaverse as a dreamscape… the birth of a new alternate world.

OK, enough of that…

The main difficulty I had in creating this image stems from the fact that the reflection in the chrome ball is actually the real reflection of the CGI environment.  It’s not a composite.  The mountains actually go all the way around the environment.  The grid floor goes out in all directions.  The “planet” and the “sun” seen in the ball are on the HRDI dome over the scene that is creating the ambient light.  The dome had to be lined up so the “planet” reflected in the sphere correctly.  The mountains had to be rotated in such a way that the peaks behind her and the ones in the chrome ball both looked good.  The main light in the scene is the keylight on the character which can be seen in the chrome sphere as a bright rectangle in the upper left of the sphere.  I could have removed that in post but I left it in because that’s the point.

The metaverse was supposed to be the future of everything.  Facebook even changed their name to Meta.  Now AI is the new thing.  Will the metaverse be created?  Will AI create the metaverse for us?  Who knows…

Created in DAZ Studio 4.20
Rendered with Iray
Color Correction in Capture One

Invasion!

Leave a reply

It’s been some time since I’ve posted any of my 3D creations.  This is actually something I started several years ago but never finished.  I had trouble with the lighting but it all came together recently when I decided to make it a night invasion.

Created in DAZ Studio 4.21
Rendered with Iray
Color Correction in Capture One