Upload a photo, describe the motion you want, and generate a short AI video. Free credits to get started, with the credit cost for each generation shown upfront before you commit.
An AI image-to-video generator starts with one still image and a written direction for movement. Instead of assembling a slideshow or manually animating keyframes, use a photo to video workflow to describe the short moment you want, then choose the available settings before generating.
Choose a source image with a clear subject and intentional composition. Product images, food scenes, sports frames, and illustrations give a prompt a concrete visual starting point. Only upload source images you own or are licensed to use; no input guarantees a stable result.
Write the main action first, then add a camera movement such as a slow push-in, gentle pan, or small orbit when it supports the scene. A motion prompt is a direction, not a promise that every model will follow each word exactly.
Use environment details such as warm kitchen lighting, mountain reflections, an outdoor court, moving clouds, or a calm illustrated background. Add a constraint to preserve what matters: keep the product shape, keep the plate centered, or keep the composition stable.
New accounts get free credits to try the generator right away, and every generation shows its exact credit cost before you start — no guessing. Downloads have no watermark, and you can use your videos commercially as long as you own or are licensed to use the source image, in compliance with applicable law.
These source-image and generated-video pairs show focused motion directions. They are examples, not a promise that every image will produce the same result. See Showcases for more existing examples, including illustration work.
Product image: ski goggles remain the focus while mountain reflections and light provide a small, controlled sense of motion. This can help a viewer inspect a product detail without turning the image into an unrelated scene.
Example input/output pairFood scene: visible ingredients and preparation context support a prompt about steam, stirring, or a slow pan across the dish. Use the source image to establish the food and composition, then describe only the intended short action.
Example input/output pairSports scene: the player, court, and direction of play provide context for a short movement prompt. A possible use is adding a brief active moment to an editorial, social, or concept sequence built from licensed source material.
Example input/output pairModel, duration, resolution, and aspect ratio are separate choices — each one shapes your result and the credit cost, both shown clearly before you generate.
Each model offers its own set of resolution options, shown live in the generator when you select it.
Use duration for the length of the moment you want to generate and aspect ratio for the composition that fits the destination. A vertical product or food clip and a wider sports scene may need different framing decisions.
Model, duration, resolution and other choices can change the credit cost — the generator always shows the total before you start, so there's no surprise after generating.
If a result doesn't match what you wanted, make one focused change — clarify the prompt, simplify the scene, or pick another setting — and generate again.
Review the available settings and credit cost before starting your generation.
Choose an image you own or are licensed to use.
Write the movement or camera direction you want.
Check the available choices and cost before you start.
Start the generation, then download the result when it is ready.
Answers about accounts, credits, generation, downloads, and source-image rights.
Sign up for free credits, review the cost before generation, and create a short video from your image.