Image-led motion
animate an established visual starting point.
Video generation
Turn a starting image or visual references into a timed video shot.
Loading model settings…
Your prompt, settings, and references stay together in a new Canvas.
01 / Meet the model
Vidu Q4 creates video from a first frame or visual-reference inputs. It requires imagery rather than a text-only request, with optional generated audio and several output resolutions. Describe one coherent motion and choose enough time for it to develop before reviewing the full clip.
02 / Choose it for
animate an established visual starting point.
guide a shot with selected images.
compare supported duration and resolution settings.
03 / Before you create
Model settings. Availability, input mode, and references can narrow the choices offered in Canvas.
04 / A closer look
No. Supply a starting image or supported visual references, then describe the motion. Text gives direction but does not replace the required image input.
Text prompt · Reference images · Start frame. The input controls above show the options available for your selected mode.
1:1 · 16:9 · 9:16 · 3:4 · 4:3. 540p · 720p · 1080p · 2K · 4K. The composer on this page accepts image references and frames; video/audio reference uploads are not exposed here.
Start with the format you intend to publish, then choose the available output settings. Changing inputs can change the choices. Review the current Gem estimate before Generate; availability and cost can vary.