Image-to-Video Motion Direction

Animate a still image by directing only camera and motion: the discipline that stops image-to-video from mangling your original.

[Attach your image, then direct ONLY the motion, never re-describe what's in the image:]

Camera: [ONE MOVE: "slow push-in toward the subject" / "gentle handheld drift, as if someone is holding the shot" / "smooth lateral track left to right" / "slow pull-back revealing the wider scene"], [PACE: subtle and slow / deliberate].

Subject motion: [WHAT MOVES AND HOW MUCH, keep it faithful to the still: "her hair lifts slightly in the breeze, she blinks and her smile deepens" / "steam rises from the cup; nothing else moves" / "the water surface ripples gently, reflections wobbling"].

Environment motion: [SECONDARY LIFE: "leaves drift past in the foreground" / "dust motes float through the light beam" / "clouds crawl almost imperceptibly"].

Everything else in the image stays exactly as it is, same composition, colors, lighting, and details as the source image.

Audio: [MATCH THE SCENE: "soft wind, distant birds" / "café murmur, cup on saucer"]. No music.

Duration: [4-8s], ending on a stable frame.

How to use

The cardinal rule: the image defines what things look like; your prompt defines only what moves. Re-describing the image's contents invites the model to repaint them. Start subtle (one camera move plus one or two motion layers) because every extra moving element raises the chance of warping. Works in Veo, Kling, Runway, and Luma; Veo adds native audio, and Luma's keyframes give the most precise control over start and end states.

More video prompts

[Attach your first frame image, and the last frame image if your tool supports it, then use this prompt:]

Animate from the first image to the last image.

What changes between them: [THE ONE TRANSFORMATION, e.g. "the closed box opens and the product rises out of it" / "the empty street fills with morning light" / "the character turns fro

First and Last Frame Control

Direct a video model between two fixed images so the motion, timing, and transition land exactly where you need them for an edit.

Videointermediate

Generate a sequence of shots featuring the same character.

**Step 1: write the character lock.** This exact text goes into every shot prompt, word for word, before anything else. Never paraphrase it.

CHARACTER LOCK:
"[NAME], a [AGE] year old [DESCRIPTION: build, height impression], with [HAIR: exact length, color, texture, and how it is

Multi-Shot Character Consistency

Keep one character looking like the same person across separately generated shots using a locked description block and fixed style spine.

Videoadvanced

Write and shot-list an explainer video.

What we are explaining: [PRODUCT, FEATURE, OR CONCEPT]
Who is watching and what they already know: [AUDIENCE + BASELINE]
The one thing they should understand afterward: [THE SINGLE TAKEAWAY]
What they should do next: [THE ACTION]
Length: [60 / 90 / 120 seconds]
Visual style: [SCREEN RECORDING / MOT

Explainer Video

Turn a product or concept into a 60 to 90 second explainer with a script timed to shots, so the visuals carry what the words cannot.