Directing note: when the docs are silent

Many points on the register read “None in the docs”. That records the documentation, not the model's ability. As of 2026-09-25.

A silent point is worth testing on a short clip before a scene depends on it.

Docs also change: one camera control on the register was retired months before the reading.

1From the docs

Negative prompts are a tool that helps specify the elements that you don't want generated in your video.

Google Cloud, Veo video prompt guide

You may describe how the camera should behave in the prompt including the speed at which it moves, though the effects may not be consistent or 100% effective

Leonardo.Ai Help Center, generating video

Multiple keyframe support

Lightricks, LTX-Video repository

• Negative prompts
  Negative prompts list elements that should not appear in the videoGoogle Cloud, Veo video prompt guide / recorded 2026-09-25
• Camera Movement
  Camera behaviour can also be written into the prompt, with a warning that the effect may not be consistentLeonardo.Ai Help Center, generating video / recorded 2026-09-25
• Advanced features
  The model supports several keyframes, not only a first frameLightricks, LTX-Video repository / recorded 2026-09-25
• Retirement notice
  The camera control feature belonged to Gen-3 Alpha Turbo, retired on July 30, 2026Runway, camera control on Gen-3 Alpha Turbo / recorded 2026-09-25
• Camera
  Camera motion options to pick: zoom in or out, move left or right, tilt up or down, static and handheldAdobe, Firefly help: generate videos using text prompts / recorded 2026-09-25
• Camera motion
  Camera moves are prompt words, each defined with an example: static, pan, tilt, dolly and moreGoogle Cloud, Veo video prompt guide / recorded 2026-09-25
• Example request
  Camera moves are written in the prompt, as in its example of panning outxAI, Grok Imagine documentation / recorded 2026-09-25
• Camera controls
  More than fifty named motion presets, from crash zooms to crane shots and bullet timeHiggsfield, camera controls / recorded 2026-09-25

2Camera language in a pipeline

Where “When the docs are silent” has to be written by hand, SceneMixer's pipeline writes the shots; its guides explain:

SceneMixer writes dialogue into the script analysis, assigns each line to a shot with a speaker and a short delivery note, and the video model performs it — picture and audio generated together, so the mouth forms that sentence in the language you chose.

SceneMixer, AI Dialogue Generator (read 2026-10-13)

A location can hold multiple sub-plates for different camera positions, generated together, so cutting around a space stays coherent.

SceneMixer, AI Scene Generator — “Can one location have several camera angles?” (read 2026-10-13)

3Other notes

• Moves from references
• Reading a prompt guide

Examples are quoted from the models' docs; no model was run.