Order is the object. A pile of generated stills is a batch; a slideshow is those stills in a locked sequence, each able to carry its own overlay copy, then optionally rendered as a video with a hold duration and a transition between plates. You can start from photos you already have or from a prompt that plans and fills the plates — those are two jobs, and mixing them is how you generate art you were going to throw away, or fail because there were no stills to arrange.
That is why it is not text-to-image, which returns one still, and not batch-generation, which returns several takes of one brief. The carousel is the native post. Converting the same stack to a reel is a second format of the same object, not a new idea: the slides were already paid for; the convert pass sets pace, transition and whether the overlay-stamped versions travel with it.
The slideshows hub is recipes to recreate. Edit, replace or reorder slides before the convert pass — cutting the exported MP4 afterwards is the expensive direction.
In practice
- Decide photo-in or prompt-planned before you start; the two jobs do not share an input shape.
- Lock slide order and per-slide copy while it is still a stack of images.
- If you stamped text on the plates, take the edited versions into the video render or the captions stay behind.
The mistake to avoid
Dumping a batch of stills into a convert and expecting a carousel. Without a locked order and per-slide copy it reads as a shuffle, which is a batch you exported.
Go deeper
A prompt-built slideshow is planned slides, not your photo dump
create_slideshow plans and fills slides from a prompt. Uploading your own photos is a different job, and mixing them wastes credits.
Where you will run into it
- Turn a Slideshow Into a Video — The carousel you already made, republished as a reel.
- AI Slideshow Maker — Photos in. Scroll-stopping slideshow out.
Related terms
Text-to-image
Text-to-image renders a still picture from a written description, with no picture going in.
Batch generation
Batch generation runs one brief as several jobs at once — multiple variants, models or formats — so the comparison happens in a single sitting instead of across a week.
Content repurposing
Repurposing is turning one finished piece into the several format-native cuts each platform expects, rather than posting the same file to all of them.
Recurring series
A recurring series is a saved workflow or slideshow premise put on a schedule, so each run writes a new episode against the same cast and format.
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.
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.