The rise of the AI V: In my previous post over AI generated, many - correctly - pointed out that there were many defects, especially with the hands, plastiky skin, etc. Being myself...

jlg1000 Loc: Uruguay / South America

In my previous post over AI generated, many - correctly - pointed out that there were many defects, especially with the hands, plastiky skin, etc.

Being myself involved in AI research, I continued improving on the matter and wanted to share a sample of my latest results. BTW I've got new hardware... this partly allows me to create more complex imaginery.

As before, Many will ahhh... point out, that it this is not the place for such a post and that it should be ostracized to some obscure sub-forum.

Still, I believe I belongs here - and of course NOT in the photo gallery - because my intentions are to inform this prestigious community on the state of the art on AI image creation and to stir discussion on how it might affect photography.

Full disclosure: ** No, they are not real and I did not use any photo of any kind **

(Download)

SkyKing Loc: Thompson Ridge, NY

…The advertising world alone is going to feast on this…!

Retired CPO Loc: Travel full time in an RV

They keep getting better!!

bsprague Loc: Lacey, WA, USA

I like them! Can you tell more about the hardware, software and workflow? Please!

Boris77

jlg1000 wrote:

In my previous post over AI generated, many - corr... (show quote)

So someone else took some photos so that a machine could index them so that you could call them up and rearrange a few pixals to create a new image of no emotional value. Another step forward for society.
I am looking forward to the newly discovered pictures of MM.
Boris

Blenheim Orange Loc: Michigan

jlg1000 wrote:

I did not use any photo of any kind

Photos are used for this process.

JohnSwanda Loc: San Francisco

jlg1000 wrote:

In my previous post over AI generated, many - corr... (show quote)

I don't think it belongs here or the photo gallery, it belongs in the AI section, because that's what it is about.

jlg1000 Loc: Uruguay / South America

JohnSwanda wrote:

I don't think it belongs here or the photo gallery, it belongs in the AI section, because that's what it is about.

It would if it were intended as a showcase of pieces of art.

I believe this post belongs here because it is intended to stirr discussion and inform the photographers

jlg1000 Loc: Uruguay / South America

Blenheim Orange wrote:

Photos are used for this process.

In a sense yes...
In a sense no...

And in a sense, a Art student trained her/his/it's brain to create images by... looking to other's images. I don't find it too differently.

Let my explain with some images of my creation... they aren't meant to resemble photos, still they were created by the very same trained predictive models.

jlg1000 Loc: Uruguay / South America

Boris77 wrote:

So someone else took some photos so that a machine could index them so that you could call them up and rearrange a few pixals to create a new image of no emotional value. Another step forward for society.
I am looking forward to the newly discovered pictures of MM.
Boris

This is not how it works. No index, no rearrangement.

The weights of a neural network are trained to predict an outcome, it is the very method that ChatGPT uses and I've been able to create music with it... every child does the same when he learns to speak, draw or sing.

Curmudgeon Loc: SE Arizona

I am going to watch this with interest. Like bsprague, I would like to know more about your workflow, what AI site(s) you use. Creating head shots like that is relatively simple on most AI sites, just the right words in the right order. With AI the devil is in the details, fingers, toes, how objects are held or used. Fingers have improved a lot since I started using AI, toes not so much. Subjects using or holding weapons, ancient or modern, tools of all sorts is still a crap shoot.

NickGee Loc: Pacific Northwest

Meh ...

Blenheim Orange Loc: Michigan

jlg1000 wrote:

And in a sense, a Art student trained her/his/it's brain to create images by... looking to other's images. I don't find it too differently.

Yeah, that is the argument. "What's the difference between a human being and a machine?" It is a pretty disturbing line of thinking.

jlg1000 Loc: Uruguay / South America

Curmudgeon wrote:

I am going to watch this with interest. Like bsprague, I would like to know more about your workflow, what AI site(s) you use. Creating head shots like that is relatively simple on most AI sites, just the right words in the right order. With AI the devil is in the details, fingers, toes, how objects are held or used. Fingers have improved a lot since I started using AI, toes not so much. Subjects using or holding weapons, ancient or modern, tools of all sorts is still a crap shoot.

Hi,

I do not use any AI site, I work completely offline... I've downloaded and modded the open source software and also the models.

Everything is open source, no "setup.exe", no support but the forums. If it doesn't work, you fix it.

My system runs on Ubuntu Linux 22.04, an i9-13900 CPU and a Nvidia RTX 4090 GPU (air cooled).

I'm heavily using Stability AI's Stable Diffusion (modded), and ComfyUI (also modded) as a Workflow Manager and UI because of the flexibility. I also use a bunch of python scripts written by myself.

This is the workflow that created the pseudo-photos (as you can see, it's currently running):

JohnSwanda Loc: San Francisco

jlg1000 wrote:

It would if it were intended as a showcase of pieces of art.

I believe this post belongs here because it is intended to stirr discussion and inform the photographers

How is that different than posting about another art medium, say painting, and claim it is to inform photographers what is going on in making paintings, maybe photorealistic paintings to tie it in with photography?