Can the model render on-screen text?

Short labels sometimes come out legible on Cinematic, but text is unreliable across all tiers. Add titles and captions in your editor instead.

How do I keep a character consistent between shots?

Describe the character with the same three or four attributes in every prompt, and render all shots on the same tier. For stronger consistency, animate from a reference image using photo animation.

What aspect ratio should explainers use?

Wide 16:9 for websites and presentations, 9:16 for vertical social feeds, 1:1 for square placements. Pick once and apply it to every shot.

How many credits does a one-minute explainer need?

Roughly twelve five-second shots on Standard at 720p is three hundred and sixty credits. Drafting each shot first adds about sixty credits and usually saves more than that in rerenders.

Who owns the explainer clips?

You do. The terms at /terms-of-service grant you whatever the service produces at your direction. Copyright protection for generated content is not uniform across countries, so ask a lawyer if you need a formal position.

Guide

Explainer clips in a consistent animated style

Explainers are built from short, clear shots. Describe each one in the same visual language, render them on the same tier, and they cut together as one piece.

Open the studio Compare tiers

Sample renders

More examples

Standard720p · 5s

Macro shot of espresso pouring into a white ceramic cup on a marble counter, crema swirling, soft window light, shallow depth of field

Standard720p · 6s

Clean 3D animation of a paper airplane flying through a bright minimalist office, pastel colors, smooth camera follow, flat lighting for an explainer video

Standard720p · 5s

A white running sneaker rotating on a glossy black turntable, studio product lighting, subtle rim light, clean background for an advertisement

Pick a style and keep it

The models can produce a wide range of animated looks, but an explainer only works if every shot shares one. Decide on a style phrase up front, such as "clean 3D render, pastel palette, flat lighting" or "flat vector illustration, thick outlines, two-tone", and paste it unchanged at the start of every prompt. Then vary only the subject and the action.

The Standard tier is the natural home for this work. Stylised scenes have fewer fine textures for the model to struggle with, so Standard's output is already clean, and six credits per second keeps a ten-shot explainer within a single Starter month.

Plan shots, not a script

Write the voiceover first, then break it into sentences. Each sentence becomes one shot and one prompt. A four to six second clip comfortably covers one spoken sentence, which keeps your clip lengths short and your credit spend predictable. Shots that need to breathe, such as a title or a closing logo moment, can run longer on Draft.

Describe a single metaphor per shot. "A growing stack of coins" reads instantly; "a dashboard with charts, a team high-fiving and a rocket" does not. The models will try to render everything you mention, and crowded frames lose the point.

One sentence of narration per shot
One visual metaphor per shot
Same style phrase at the start of every prompt
Same tier, same aspect ratio, same frame rate across the set

Sound, or no sound

Explainers normally carry a recorded voiceover and a music bed added in the edit, so switch the generated sound off to avoid conflicting ambience. If you want incidental effects such as a click or a whoosh, leave it on and keep the ones that help; the picture is rendered the same either way.

Assembling the piece

Download each finished shot from your library and drop them on a timeline in any editor. Because every clip is an H.264 MP4 at the same resolution and frame rate, they concatenate without re-encoding surprises. Leave half a second of handle on each clip when you render so that cross-dissolves have material to work with.

If a single shot lets the set down, rerun just that prompt rather than the whole batch. For the hero shot, where the product or idea is revealed, a Cinematic render at 720p is often worth the extra credits; everything around it can stay on Standard.

Tier specifications

Tier	DraftFast previews	StandardEveryday quality	CinematicTop fidelity
Model class	Lightweight diffusion video model	Compact audio-video model	Full-size audio-video model
Resolutions	720p / 1080p	480p / 720p	480p / 720p / 1080p
Clip length	1–20 s	4–15 s	4–15 s
Frame rate	24 fps or 48 fps	24 fps	24 fps
Sound	Optional track	Generated with the picture	Generated with the picture
Credits per second at 480p	—	3	6
Credits per second at 720p	1	6	12
Credits per second at 1080p	3	—	30

Questions

Can the model render on-screen text?: Short labels sometimes come out legible on Cinematic, but text is unreliable across all tiers. Add titles and captions in your editor instead.
How do I keep a character consistent between shots?: Describe the character with the same three or four attributes in every prompt, and render all shots on the same tier. For stronger consistency, animate from a reference image using photo animation.
What aspect ratio should explainers use?: Wide 16:9 for websites and presentations, 9:16 for vertical social feeds, 1:1 for square placements. Pick once and apply it to every shot.
How many credits does a one-minute explainer need?: Roughly twelve five-second shots on Standard at 720p is three hundred and sixty credits. Drafting each shot first adds about sixty credits and usually saves more than that in rerenders.
Who owns the explainer clips?: You do. The terms at /terms-of-service grant you whatever the service produces at your direction. Copyright protection for generated content is not uniform across countries, so ask a lawyer if you need a formal position.

Storyboard your first explainer

Render the opening shot on Draft with your style phrase, then lock the look and build out the rest on Standard.

Generate a video