Pick the input role before the model name
| Input | Meaning | Do not assume |
|---|---|---|
| Starting image | The intended first frame of the animation. | That every reference image is automatically the first frame. |
| End frame | A target finish where the route supports it. | Support on every Turbo/standard variant. |
| Reference image set | Appearance or identity constraints in a supported mode. | Identical behavior to a starting-frame route. |
| Source video | A motion/edit reference for a compatible workflow. | That a still-image route can accept a video. |
Affiliate link: we may earn a commission if you subscribe. Your model choice comes first. How links work
From photo to reviewed clip
-
Use a licensed photo and obtain likeness permissions.
-
Confirm image-to-video input role, duration and delivery ratio.
-
Crop without hiding essential product geometry or facial features.
-
Upload the starting image; describe movement rather than a new scene.
-
Check the estimate and select a short supported duration.
-
Inspect hands, faces, labels, reflections and the last frame. Repair failures before export.
A first motion brief
Brief: “Animate this starting image as one continuous shot. Keep the mug still; let a thin ribbon of steam rise.
Use a slow camera push-in and stable window light. Add no objects, captions or music.”
For people, begin with a glance or small head turn. For products, preserve the silhouette and move the camera/light.
Repair the source before adding complexity
Improve blurry faces or labels before animation. Typeset final brand text in an editor.
For a source performance, choose motion references. For dialogue, verify native audio and review pronunciation and lip movement separately.
Sources
Sources checked 2026-10-07. Workflow recommendations are editorial guidance.