Zero Kit AI

Image to video AI: turn any image into a video

Start from a photo or an illustration, describe what happens and how the camera moves, and pick a video model. Set a first frame, or a first and last frame, to control where the clip begins and ends.

  • Nothing to install

Image to video examples with the prompts used

Hover a photo to watch the same still image start moving.

Turn a product photo into a video

A studio sneaker photo turned into a slow orbiting product shot

Prompt slow camera orbit around the sneaker, soft studio light

Made with Seedance 2.0 Mini

Try this

Turn a landscape photo into a drone shot

A mountain lake photo turned into a forward drone flight

Prompt slow drone push forward over the lake toward the mountains

Made with Seedance 2.0 Mini

Try this

Bring an illustration to life

An anime-style illustration with hair, scarf and petals moving in the wind

Prompt her hair and scarf move in the wind, petals drift across the frame

Made with Seedance 2.0 Mini

Try this

Turn a city photo into a moving scene

A night street with passing cars, light trails and flickering signs

Prompt cars pass with light trails, neon signs flicker, camera slowly pans right

Made with Seedance 2.0 Mini

Try this

How to turn an image into a video with AI

  1. 1

    Add the image

    In video mode, choose how the image is used: First & Last Frame, Universal Reference or Multi-Frame. Then add your image. Uploading asks you to sign in.

  2. 2

    Describe the motion

    A prompt is required. Say what moves, how the camera moves and how fast, for example "slow drone push forward over the lake".

  3. 3

    Pick a model and settings

    Choose a video model, then the aspect ratio, resolution and length it offers. The model list shows each model's credits per second.

  4. 4

    Generate and download

    Click Generate. The clip opens in a new conversation when it is ready, where you can watch and download it.

First frame, last frame or reference

The reference mode decides how the video model uses your images:

  • First & Last Frame: the clip starts on your image. Add a second image as the last frame and the model moves from one to the other.
  • Universal Reference: up to six images guide the look of the subject and scene, without fixing the first frame.
  • Multi-Frame: two or more images become key frames that the clip passes through in order.
  • Modes a model does not support are greyed out.

Prompts for image to video

The model can already see the image, so spend the prompt on movement. Name the subject's action, the camera move and the pace:

  • "Slow camera orbit around the product, soft studio light"
  • "The dancer spins once and the skirt flares out, camera static"
  • "Rain starts to fall and people open umbrellas, slow pan left"
  • "Push in slowly toward the window as the lights turn on"

Choosing a video model

Video models differ in resolution, length, how faithfully they keep the first frame and how much motion they add. Each model offers only the lengths and resolutions it supports, and the editor adjusts the settings when you switch.

The examples on this page were made with Seedance 2.0 Mini, which is named under each one. Models marked with a lock need a higher plan. The editor has no sound setting, so add music or a voice-over in a video editor afterwards.

Image to video or the photo animator

Image to video gives you the full set of controls: a choice of models, a written prompt, camera moves and first and last frames. The photo animator is the quick option: upload a photo, optionally describe the motion, and get a 5 or 10 second clip from one fixed model.

Common questions

Related tools

Try it on your own photo

Open the tool