How do I write a text-to-video prompt in Powtoon Imagine?

When you generate a video in Powtoon Imagine, the quality of your prompt directly shapes the result. This article explains how to structure your prompt so Powtoon Imagine produces a video that matches your intent.

Note: This article does not cover every model, plan, or AI Credits requirement for text-to-video generation. Check the Powtoon Imagine feature page or your plan details for eligibility information.

In this article

• Prompt elements
• Using a reference image
• Negative prompts
• Aspect ratios

Prompt elements

A text-to-video prompt in Powtoon Imagine can include up to eight elements. You do not need to use all of them — start with the ones that matter most for your scene and add more to refine the output.

Subject — The person, object, animal, or scene you want in the video. Start here. This is the most important element of your prompt.

Context — The background or setting for the subject. Describe where the scene takes place.

Action — What the subject is doing. Be specific: "a woman walking through a crowded market" gives better results than "a woman in a market."

Style — The visual look and feel. Examples include film noir, cartoon, surreal, vintage, or futuristic.

Camera motion — Optional. Describe how the camera moves, such as aerial view, tracking shot, or point-of-view (POV) shot.

Composition — How the shot is framed. Examples include wide shot, close-up, or over-the-shoulder.

Ambiance — Lighting, color palette, or mood. Examples include golden hour lighting, muted tones, or tense atmosphere.

Audio — Sound effects, music, or speech. Audio description is supported when using the Veo 3 model.

A well-structured prompt combines several of these elements in a single description. For example: "A fox running through a snowy forest at dusk, tracking shot, cinematic style, soft blue lighting."

Using a reference image

If you want to generate a video from an existing image, use the image-to-video workflow. The input image becomes the first frame of the generated video — it is not used as a general style reference.

1. Create an image using Text-to-Image in Powtoon Imagine.
2. Open Powtoon Studio and select that image as your reference for video generation.
3. Write your prompt to describe the action that continues from that first frame.
4. If the image contains multiple people or subjects, name the specific subject that should act or speak in your prompt.

Note: The reference image sets the opening frame of the video. Powtoon Imagine generates motion forward from that point based on your prompt.

Negative prompts

Use negative prompts to tell Powtoon Imagine what to leave out of the generated video. Negative prompts work best when you describe the unwanted element directly, rather than using instructive wording like "no" or "don't."

• ► Instead of no walls, write wall, frame.
• ► Instead of don't include text, write text, captions, subtitles.

List unwanted elements as plain descriptive terms, separated by commas.

Aspect ratios

Choose your aspect ratio based on how the video will be used.

16:9 (widescreen) — Use this for landscape layouts or scenes where you want more background visible in the frame. This is the standard format for most screens and presentations.

9:16 (portrait) — Use this for tall subjects or short-form video formats, such as social media stories or vertical feeds.