Prompt guide

Image To Video Prompt

Turn a still image idea into a controlled video prompt with motion, camera, duration, aspect ratio, and failure-mode guardrails.

Try it here

Mini prompt studio

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

Prompt

Create a clean image-to-video generation from the reference image. Subject anchor: a close-up product photo of a matte ceramic coffee cup beside a morning window. Motion: steam rises while the camera makes a slow dolly push toward the logo-free cup. Camera: dolly movement with a clear beginning, middle, and ending. Visual style: premium studio lighting, crisp detail, clean background. Constraints: use the provided image as the first frame; preserve package shape, label placement, color, and material finish; do not invent new major objects; keep the background layout consistent unless motion is requested; compose for 9:16 and 8s. Model rewrite: Keep the prompt explicit, visual, and model-neutral.

image to video prompt

What matters

Start by naming what must stay identical from the image: subject, face, product shape, labels, clothing, and background layout.
Add one primary motion idea instead of asking for several scene changes in one short clip.
Lock the camera path, aspect ratio, and duration so the model has a clear shot container.

Coffee product still

Before and after prompt

Before

Make this coffee cup into a cool video.

After

Use the image as the first frame. Preserve the ceramic cup shape, handle, table edge, window light, and background layout. Create an 8s 9:16 product shot where steam rises naturally and the camera makes a slow dolly push-in. Keep the cup centered, crisp, and realistic. Negative prompt: warped cup, changing handle, fake text, camera jitter, melted edges.

Why it works

The subject anchor protects the cup shape.
The camera path is concrete.
The negative prompt targets common image-to-video artifacts.

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.