Depth → Image (ControlNet)

Upload a photo - we estimate its depth map (MiDaS) and use that 3D structure to control a generated image. Keeps the spatial layout while changing everything else.

We estimate a MiDaS depth map from this. Images with clear foreground/background separation work best.
Looser 0.7 Threta
~1,200 tokens (SDXL × 1.2 ControlNet)
Matokeo

Waeleze rafiki zako kuhusu mapenzi ya mapenzi ya Free.ai?

Pima ukurasa huu