(Jogging) (2025)
Image description: A futuristic robotic figure standing stationary against an overcast sky. The robot features a distinctive oval-shaped head with a large, prominent circular lens or visor that displays rainbow-colored reflections across its surface. Its mechanical body is constructed from white and gray metal plating with numerous exposed wires, cables, and components running across the torso and arms. The lighting is natural but diffused through heavy cloud cover, creating a gray, overcast atmosphere that casts soft shadows across the blurred mountainous landscape visible in the distance.
This is a super interesting image. Despite the prompt having zero requirements for human body shape or secondary sexual characteristics, the generator still choose to give it breasts. I wonder what that indicates about its data set and the general use of image gen
The model is probably just a bit overfit. More importantly, the image description is not the generation parameters. I wrote myself. There weren’t any generation parameters for this image.
Gotcha, I misinterpreted
I think you know.
On a more serious note, it’s interesting to put in pure nonsense as the prompt (just strings of syllables with no meaning), and see what it comes up with. It likes misshapen heads, which makes sense because it’s trained on a lot of human features, but it also likes houses, fish, and hot air balloons quite a lot for some reason. The images are in my opinion a lot more interesting than a lot of what it comes up with if you give it words.
It’s a total mystery. Nobody could possibly know.