zlacker

>>flavor+(OP)
Something…seems fishy? Like the example with the guy next to the robot figure. Their model happened to predict exactly the same type of figure?! Diffusion models are not omnipotent…

>>syntax+tl
The model gets the reference images as "context", so it can just copy the robot from one of the other images.

>>foota+Io
Ahh I see, this makes a lot more sense now!