Google · model workflow guide
Veo 3.1 Best Settings
There is no single universal preset for every shot. The useful approach is to choose settings around the job of the clip: composition, motion, continuity, output format and how expensive retries are.
How GenVideoKit structures Veo 3.1 prompts
Use coherent natural-language direction with explicit temporal flow from start state to end state. Describe subject action, camera behavior, lighting and environmental motion. When relevant, integrate dialogue, ambience and sound effects because this model family supports native audiovisual generation. Avoid conflicting camera moves and keep continuity physically plausible.
Text → videoImage → videoNative audioFirst / last frameExtension
Production shortcut
Start from the delivery format and one clear shot objective. Keep subject motion and camera motion separate, then add only the continuity constraints that matter.
Reference pricing snapshot
$0.4 / second Baseline settings workflow
1. Lock the delivery formatDecide wide, vertical or square before writing camera blocking.
2. Define one visible actionA short clip should have one dominant subject action and a readable result.
3. Add one camera moveTracking, push-in, pull-back or orbit should support the subject action rather than compete with it.
4. Protect continuityLock identity, product geometry, wardrobe, environment or lighting only when those elements must remain stable.