cinemasetfreeEstablishing shots
Describe a location, then generate its establishing shot. That image becomes the reference for scenes set at that location, so the same room looks like the same room.
Describe, then generate
Images come from text. A location with no description generates something generic. The description is the work; the picture is the easy part.
Describe
Describe asks the text model to write a visual description from what the project already knows: the script, the scene headings, the location’s own fields. Edit what comes back; it is a draft, not an answer.
Generate
Generate renders an establishing shot, combining that description with the active production design’s style prompt so everything in the project looks like it belongs to one film.
Iterate
Every generation is kept, not overwritten. Open the portrait modal to page through versions, rate them 1–10, pick the one that’s right, or upload your own image instead.
Real place, or invented one
Both are legitimate. For a location you have already found, upload photographs instead of generating. The portrait modal takes uploads, and a real photo is a better reference than an invented one.
For a location you’re still looking for, a generated establishing shot is a scouting brief: it tells a location manager what you’re after far more precisely than a paragraph does.