How to place an overlay exactly where you want it instead of nudging it
Ask Vizard Agent to put a coordinate grid over a representative frame before it places anything. You then read the position and the size straight off the picture and give it numbers, instead of the two of you converging on a spot through a series of "a bit lower" adjustments that each cost a render.
What do you type into Vizard Agent?
Ask Vizard Agent for the grid rather than for the placement. The instinct is to describe where the thing ought to go, but a description cannot be checked afterwards, whereas a number can be checked in a second. Say what the overlay must line up with: a face, a sign or an edge.
Prompt
What does Vizard Agent actually do?
It measures instead of negotiating. Vizard Agent uses the same handful of steps whether it is locating a UI element, a number plate, a panel, a face or a printed logo on a box. It reads the grid at full resolution, because coordinates taken off a preview are scaled and land wrong by exactly the scaling factor. In the sessions behind this article it:
- Extracted a representative frame at full resolution and rendered a coordinate grid over it.
- Read the target's position off the grid, and its extent as well, since the size decides whether a graphic clears the target, covers it or sits beside it.
- Placed the overlay at those coordinates.
- Rendered a frame with the overlay on it and compared it against the grid measurement, because an overlay anchored from its centre lands wrong when its corner was measured.
- Repeated the measurement on other frames when the target moved, gridding the frames at each end rather than assuming the middle.
When does this not work well?
A grid measures one frame, and Vizard Agent will say when that is not enough. A target moving unpredictably needs tracking, not measuring. Each change of shot size needs its own measurement, the grid may be coarser than a very small element, and a measured position is not the same thing as a good composition.
Common questions
Why not just say lower? Because "lower" cannot be checked, and Vizard Agent cannot verify a guess.
Does the grid appear in the video? No. Vizard Agent renders it only on the measuring frame.
What if the target moves? Then Vizard Agent grids several frames and tracks between them.