The format is locked before you arrive. Finger-snap, mugshot and the rest of the templates shelf already decided the motion, the cut and the joke; your job is to supply the still the template is built to consume, usually a photo. The run starts once every required input is a hosted URL, and a live card tracks the finished clip.
A saved workflow is the opposite shape: you author scenes, you can edit them, you clone a public recipe and swap the asset map. A style-preset is a look on one generation, not a finished clip. Content-repurposing takes a piece you already made and recrops it; a one-tap template makes the piece.
There is no scene plan to approve. If you needed per-shot models and a combine step, you wanted the movie or the workflow, not this shelf.
In practice
- Attach the photo the template actually lists — a missing still is a failed run, not a prompt you can talk past.
- Pick the format for the joke it already tells, then recast with your still; do not fight the motion.
- If you need to change scene order or swap a product mid-recipe, you are in a workflow, not a template.
The mistake to avoid
Sending a one-tap template a paragraph of plot, or cloning a workflow for a format that only wanted the photo. The template never received the still it is built to consume.
Go deeper
Trend templates vs custom videos for brands
Trend templates or custom AI videos? A decision framework for brands: cost, speed, reach, and conversion trade-offs, plus a weekly mix that uses both.
Related terms
Saved workflow
A saved workflow is a reusable video recipe — scenes, assets, style and model stored so you can run it again with a fresh plot.
Style preset
A style preset is a named look — cinematic, anime, documentary — that a model applies without you having to describe it in the prompt.
Content repurposing
Content repurposing meaning: turning one finished piece into format-native cuts per platform, not posting the same file everywhere.
Text-to-video
Text-to-video is generation from a written prompt alone — you describe a shot, the model invents every frame of it, and no image or footage goes in.
Image-to-video
Image-to-video animates a still you supply: the picture becomes the opening frame, and the prompt describes only what happens next.
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync — in your browser or on your phone.
Free on iPhone. On a computer? The same account works on Versely Web, no install needed.