Text-to-video and image-to-video that begin from your stills. One movement per clip; price by duration and resolution, shown before you confirm.
Video is priced by duration and resolution. The exact credit cost is calculated on the job and shown before you confirm; failed jobs refund automatically.
Video is the most expensive entry in this directory, so it is approached through the index rather than at random. The dependable order is: a still first — on character, already culled — and then a single movement laid over it. For scenes that exist nowhere yet, a text brief carrying the same character entry as your stills keeps the woman in motion identical to the woman at rest. Pricing follows duration and resolution, is calculated per job, and is printed in full before you confirm. A failed render refunds itself.
Think of each clip as a cross-reference. It points back to an entry — a character, a set, a still that already earned its place — and adds exactly one new fact: movement. Clips briefed as sequels behave. Clips briefed as fresh inventions compete with your own catalogue, and the catalogue usually loses.
Image-to-video inherits the woman, the outfit and the room from its first frame. It is the cheapest consistency in the directory and the easiest to file.
A turn toward the window. A slow step forward. One movement, camera held. Choreography smears; a single gesture renders cleanly and loops well.
Decide where the clip will be listed before rendering it. A teaser and a store piece are different sizes, and rendering the maximum of everything quietly doubles a budget.
The strongest frame of the week, given a few seconds of life, pointing viewers toward the full set it heads.
One clean repeating gesture that reads at thumbnail size and survives platform compression.
Longer takes briefed from the same entry as the neighbouring stills, so nothing in the listing feels cast twice.
“She turns slowly toward the harbour light at the window and lowers her gaze, hair swaying slightly, camera still.”
One movement for the subject, none for the camera. The first frame already decided everything else, so the brief only directs motion.
“Fictional 34-year-old woman, jet-black hair in a low ponytail tied with a mint silk scarf, deep teal evening dress, walking slowly across a quiet hotel lounge toward camera, warm low light, unhurried, cinematic.”
The filed entry travels into the clip brief word for word, so the woman in motion is the woman in the stills.
| Lever | Effect on price | Practice |
|---|---|---|
| Duration | Longer costs more | A teaser rarely needs more than a few seconds |
| Resolution | Higher costs more | Render at the destination size; upscale a winner later |
| Retries | Each render is a job | Correct the brief or the first frame before rendering again |
By duration and resolution, calculated per job and shown before you confirm. Nothing is charged unseen, and a failed render refunds automatically.
Image-to-video for series work, because the first frame carries the character with it. Text-to-video suits standalone scenes and first experiments.
Yes, by two habits: start from series stills, and carry the filed character entry into text briefs word for word.
Usually too much is asked of it — several movements, a moving camera, a crowded room. One movement, a still camera and an uncluttered space is the pattern that holds.
No. Clips rest in your account until you publish or download them. Nothing is posted on your behalf.
Drafts, edits, animation and finishing share one credit balance and one private library. Start with the piece you need today.
Open the generator