Give the product a role
Use product images alongside visual or motion references to direct a scene up to 30 seconds. Check the shape and details in the result.
Keep in mind
Output goes up to 1080p. References guide the result; they do not guarantee an identical face or object.
Give references a clear role
A 1080p option for image-led scenes, reference-guided work and video transformation. Plan what each reference should control.
Keep in mind
Inputs and audio behavior differ between modes. A storyboard is direction, not a promise that every cut will match.
Direct the beginning and end
Use opening and ending frames, mix references or extend a clip, with generation lengths up to 30 seconds.
Keep in mind
For video input and extension, source plus generated duration must fit within the 30-second limit.
Plan where the scene lands
Use a first and last frame to shape a transition, or extend an existing clip. Generate 5–20 seconds at 720p or 1080p with optional audio.
Keep in mind
Frame control is different from a mixed-reference workflow. This model does not offer a separate reference-to-video mode.
Build around an audio track
Use text or an image, or choose audio-to-video with an owned audio file to guide a 1080p scene.
Keep in mind
Audio-to-video requires an audio input. Text and image modes have a different set of available settings.
How we choose
Seedance 2.5 and Kling Omni Pro lead for reference-led product stories. Wan 3 Prime adds source editing, FLUX 3 lets you set the opening and closing image, and LTX 2.5 Pro is useful when a supplied soundtrack drives the scene. Check the product shape in every shot.
This is an editorial order for starting your tests, not a measured quality ranking. We consider the available inputs, duration, audio and output options for this task. The clips use different prompts and settings; a single result cannot establish which model is best. Check the full model details before you create.