Prompt guide

AI Image To Video Prompt

Use one reference image as the visual anchor, then add motion in a way that reduces morphing and unstable backgrounds.

Try it here

Mini prompt studio

Change the image summary or motion and copy a focused prompt.

Prompt

Create a Veo-style image-to-video prompt from the reference image. Subject anchor: a portrait of a chef holding a plated dessert in a warmly lit restaurant kitchen. Motion: the chef smiles subtly while the dessert steam and background lights move naturally. Camera: handheld movement with a clear beginning, middle, and ending. Visual style: authentic handheld creator video, soft room light, natural expression. Constraints: use the provided image as the first frame; preserve face identity, hair, clothing, posture, and room layout; do not invent new major objects; keep the background layout consistent unless motion is requested; compose for 16:9 and 8s. Model rewrite: Use natural cinematic language with a clear shot arc and continuity cues.

ai image to video prompt

What matters

For people, prioritize identity preservation before motion or style.
Use natural micro-movements for portraits and creator-style clips.
Add hand and face failure modes when the image includes a person.

Chef portrait

Before and after prompt

Before

Make the chef move and look cinematic.

After

Use the portrait as the first frame. Preserve the chef's face, uniform, pose, plated dessert, and kitchen layout. Create an 8s 16:9 cinematic handheld shot where the chef gives a subtle smile and the dessert steam moves naturally. Keep the hands realistic and the background lights stable. Negative prompt: face drift, identity change, warped hands, background warping, camera jitter.

Why it works

The face and hands are protected first.
The motion is small enough for a portrait.
The background is told to stay stable.

FAQ

Common questions

Can I use the prompt in Seedance, Veo, Kling, or Runway?

Yes. Pick the target model in the generator and it rewrites the same image idea with model-specific emphasis.

Does the tool analyze uploaded images?

The first version works from your written image description, image URL, and motion notes. The upload is for preview while you write.

Why include a negative prompt?

Image-to-video outputs often fail through identity drift, warped text, unstable backgrounds, or jitter. The negative prompt names those failure modes directly.