AI Character Concept Images

[d.olivaw]

As with my little Elevenlabs experiment, I've periodically played around with image generation models, mostly for producing character or setting concept shots. The results have been mixed. Text -> Image is a very awkward modality, even with the most recent editing tools. I hope one day we get something more like a 'real' image editor that seamlessly integrates traditional pixel-pushing tools with smarter generative components that can treat arbitrarily segmented parts of an image, as opposed to the current process which is a cross between 'found object' art and a slot-machine.

Stepping down from my soap-box, here are some of the better results I've managed to get. This first grouping covers a RepliFemme dealership and the robots that populate it.

Showroom1.png (1.88 MiB) Viewed 373 times

Showroom2.png (1.98 MiB) Viewed 373 times

Showroom3.png (2.21 MiB) Viewed 373 times

Home7.png (2.09 MiB) Viewed 373 times

[d.olivaw]

These were generated as character concept images for a fembot in a WIP story.

2.png (2.23 MiB) Viewed 372 times

3.png (1.76 MiB) Viewed 372 times

7.png (1.72 MiB) Viewed 372 times

[d.olivaw]

And finally, these were another character concept, for a retro-SF WIP.

Rose1.png (1.9 MiB) Viewed 371 times

Rose2.png (1.88 MiB) Viewed 371 times

[Dollmaker]

Nice art so far!

[Robotman]

That's really great stuff! I want to see more of that retro-scifi setting.