How to use this pack
Replace the subject and product with your own rights-cleared inputs. Begin with one shot and one request; separate the camera movement from the subject’s action. For a dialogue prompt, enable native audio intentionally and keep the line short.
The suggested duration is an initial draft choice, not a quality score or a maximum. Veo’s curated route exposes four-, six- and eight-second controls; six seconds is the starting suggestion here.
Sources: Google Veo 3.1 prompting guide · checked 2026-10-07
Reference prompts need matching controls
A reference role must match the route. Starting images, endpoint images, image references and source videos are not interchangeable. If a control is unverified in the dataset, do not assume it exists because another provider integration has it.
Do not paste mode names into a web field that does not expose those modes. Select the equivalent supported UI route or change the brief. The model detail page keeps the dated controls and source notes.
Sources: Google Veo 3.1 prompting guide · checked 2026-10-07
Review before a second draft
-
Check subject/product identity and motion across the full clip.
-
Listen for extra words, missing sound or unwanted music.
-
Change one failed instruction at a time.
-
Proof any lettering; add important text in a finishing editor.
-
Record the exact route, settings and accepted output instead of calling every reroll a tested success.
Sources: Google Veo 3.1 prompting guide · checked 2026-10-07
Products and ads
Ceramic reveal
A cream ceramic mug on a wooden plinth at dawn. One continuous close shot with a slow push-in as steam curls upward. Soft side light, natural room tone and a gentle ceramic clink. No text or music.
- Starting settings
- Recommended starting setup: text-to-video; 16:9; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- One restrained reveal separates camera movement from object movement.
Bottle light sweep
An unbranded amber glass bottle on dark stone. Locked close-up as a soft light sweeps across its curved surface. Keep the bottle still. Quiet studio ambience, no speech or on-screen words.
- Starting settings
- Recommended starting setup: text-to-video; 16:9; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- A stationary product gives you a simple geometry check.
Coffee pour
Close shot of one hand pouring coffee into a plain cup. Fixed camera, warm kitchen light, a single continuous pour. Sound of liquid and a quiet room; no narration.
- Starting settings
- Recommended starting setup: text-to-video; 16:9; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- One action and an explicit sound cue fit a short scene.
Bag detail
A canvas tote rests on a bench. The camera tracks slowly along its stitching without changing its shape. Diffuse afternoon light and distant street ambience. No logos, text or speech.
- Starting settings
- Recommended starting setup: text-to-video; 16:9; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- Detail coverage avoids inventing product functions.
People and dialogue
Bookshop line
An adult bookseller with short grey hair stands by a shelf. Medium shot, locked camera. In a calm voice she says, “This story begins here.” Soft room tone, no music.
- Starting settings
- Recommended starting setup: text-to-video; 16:9; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- One named speaker and a short line make speech easier to review.
Workshop greeting
An adult potter wearing a blue apron looks up from a workbench and says, “Welcome to the workshop.” Gentle push-in, warm side light, quiet tools in the background. No cuts.
- Starting settings
- Recommended starting setup: text-to-video; 16:9; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- The action ends before the spoken greeting becomes complex.
Two-shot pause
Two adult friends sit across a café table. Stable medium two-shot. The person on the left asks, “Ready?” After a pause the person on the right answers, “Ready.” Quiet café ambience.
- Starting settings
- Recommended starting setup: text-to-video; 16:9; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- Speaker locations and sequential turns reduce ambiguity.
Presenter fact
An adult brand presenter stands beside a closed notebook. Locked portrait composition. She says, “Choose the size that fits your desk.” Neutral background, clear voice, no added claims.
- Starting settings
- Recommended starting setup: text-to-video; 16:9; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- A factual script avoids fabricated experience or endorsement.
Places and cinematic motion
Forest path
A narrow woodland path after rain. Low tracking shot moves gently forward past wet ferns. Diffuse morning light, birds and distant dripping water. No people, cuts or music.
- Starting settings
- Recommended starting setup: text-to-video; 16:9; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- A coherent environment anchors both motion and ambience.
Harbour dawn
Wide view of a small harbour at sunrise. Slow pan to the right as one boat moves across the water. Soft engine hum and gulls, no voiceover. Keep the horizon level.
- Starting settings
- Recommended starting setup: text-to-video; 16:9; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- One boat and a level horizon provide concrete review targets.
Station wait
An empty platform under warm evening lamps. Locked wide shot; a train passes slowly in the far background. Distant rail sound, no crowds or legible signage.
- Starting settings
- Recommended starting setup: text-to-video; 16:9; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- A distant action avoids conflicting foreground motion.
Rainy window
Close view through a rain-covered window toward a quiet street. Fixed framing, droplets slide down glass, subdued tyre sound outside. No text or music.
- Starting settings
- Recommended starting setup: text-to-video; 16:9; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- A single moving layer creates a controllable atmosphere.
Social and everyday scenes
Morning desk
A hand places a pencil beside an open blank notebook. Portrait close shot, stable camera, natural window light. Pencil tap and quiet room tone; no readable page text.
- Starting settings
- Recommended starting setup: text-to-video; 9:16; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- The small action works as a social opening beat.
Kitchen pause
An adult cook pauses beside a steaming pot, smiles and says, “Dinner is almost ready.” Medium portrait shot, locked camera, soft kitchen ambience. No extra speakers.
- Starting settings
- Recommended starting setup: text-to-video; 9:16; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- Short dialogue and a static frame support focused review.
Plant care
One hand pours a little water into a plant pot. Portrait close-up, steady overhead camera, soft room light. Gentle water sound and no narration.
- Starting settings
- Recommended starting setup: text-to-video; 9:16; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- A simple task limits simultaneous movements.
Packing scene
An adult packs one plain notebook into a canvas bag. Portrait medium shot, fixed camera, calm daylight. Fabric rustle and zip sound, no music or slogans.
- Starting settings
- Recommended starting setup: text-to-video; 9:16; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- A single brief sequence stays close to observable object actions.
Reference-led shots
Photo steam
Animate the supplied cup starting image. Preserve the cup and table composition; only steam rises as the camera inches forward. Quiet café ambience, no text or music.
- Starting settings
- Recommended starting setup: image-to-video / starting frame; 16:9; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- Movement guidance avoids redescribing a new subject.
Photo glance
Animate the supplied consenting adult portrait. Preserve facial structure and wardrobe. One small glance toward the window, stable camera and light, quiet room tone, no speech.
- Starting settings
- Recommended starting setup: image-to-video / starting frame; 16:9; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- A small head movement reduces identity stress.
Photo storefront
Animate the supplied storefront starting frame. Keep the façade intact. A soft breeze moves the awning; the camera stays fixed. Distant footsteps, no added people or signage.
- Starting settings
- Recommended starting setup: image-to-video / starting frame; 16:9; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- Explicit invariants define what should remain unchanged.
Photo shoe
Animate the supplied product still. Keep the shoe silhouette and materials fixed as the camera makes a small lateral slide. Quiet studio sound; no added branding or text.
- Starting settings
- Recommended starting setup: image-to-video / starting frame; 16:9; 6 seconds if exposed; audio on for the written sound/line; use the selected route’s default output size and verify its current options.
- Why this guidance
- A limited camera move creates a clear product-fidelity test.
Sources and verification.
Last updated 2026-10-07. Provider claims and endpoint records are dated evidence; workflow advice is editorial guidance.
- Google Veo 3.1 prompting guide Checked 2026-10-07
- Higgsfield MCP video catalog, exported 7 October 2026 Checked 2026-10-07
- Google: Veo video generation documentation Checked 2026-10-07
- Higgsfield: public plan/credit table, Italy EUR Checked 2026-10-07