Discussion about this post

User's avatar
TOM ANG's avatar

What text-to-image generates is without a camera at the production stage, so it's more of a '-gram' (the difference between a photogrraph and a photogram is whether a camera is used'. But as text-to-image doesn't involve light either, it'd help to drop the prefix 'photo-'.

Yup; we much need a new word, and with that will come a lot less confusion.

Some writers have suggested 'synthography' but I think that leaves too much room for confusion. I'd prefer 'synthogram'. The way a text-to-image image is generated is closer to writing: building up more and more detail, than to a capture process that captures at full resolution (whether line-by-line or whole frame).

Then the question is: Is a synthogram a photograph? No; it's not.

Does it look like a photograph? Yes.

Listen: a photograph can be captured to look like a watercolour, but have captured a watercolour. No; we haven't. A fortiori if we turn a photograph into a charcoal drawing-like image, it's not a charcoal drawing.

So, a synthogram is made with the help of photos. But a billion photo data-pairs does not a photo make.

You might like to subscribe to my substack Dark2Light for further thoughts. I've just written what I was going to write for my notes. Time to skip over there!

(Thanks for your work on this whole area, which reminds me of the fun we had over 20 years ago when digital was a dirty word in photography.)

Expand full comment
Michele Colonna's avatar

I would recommend taking a look at the work of Dubhz0 who’s been doing this in my opinion in the right way. Somberly, respectfully and at the same time quite uniquely dubhz0.com

Expand full comment
18 more comments...

No posts