How to turn a grandparent's story into an illustrated film
Give Vizard Agent the story and whatever photographs you have. It generates the scenes in one consistent illustrated style with the same face throughout, narrates them in the right voice and dialect, and times every shot to the length of the line that plays over it.
What do you type into Vizard Agent?
Supply the family facts as facts. Vizard Agent will otherwise have to infer relationships from the storytelling, and a video that gets a grandmother's children in the wrong order is not a video anyone in the family will forgive. Name the dialect, not just the language.
Prompt
What does Vizard Agent actually do?
A recording becomes something people will sit through once it has pictures, and the pictures have to look like the same person every time. So Vizard Agent uses the family photographs as the likeness reference for every scene, and tests the style on one scene before making the rest. In the session behind this article it:
- Read each supplied photograph in turn and checked the image tool's options for using them as a reference.
- Reviewed the voice options and their costs for the language, and searched for a voice warm enough to carry the story.
- Generated the first scene alone and read it back to check the style and likeness, then generated the other five in parallel and reviewed each.
- Generated the first narration line to check the voice and delivery, then the rest in parallel.
- Measured each audio file's duration so every scene stays on screen exactly as long as its line, then searched for music that is sad, hopeful and loyal at once.
When does this not work well?
This is a family record rather than a piece of content, so what goes wrong is exactly what a family will notice. Vizard Agent can hold the likeness steady, but names and their order are yours to confirm. With few photographs the likeness drifts, some voices handle deep dialects poorly, and six scenes covers a few minutes, not a life.
Common questions
How many photographs do I need? Two or three is workable. Vizard Agent uses them as the likeness reference for every scene.
Will the face stay the same? That is checked. Vizard Agent generates one scene first and reviews the likeness before the rest.
What about the dialect? Name it. Vizard Agent searches for a voice that handles it rather than the standard form.