Recast an existing performance video with new performers while preserving the original motion, choreography, camera work, and location, on Seedance 2.5. Try free — pay per generation, no subscription.
Recast an existing performance video with new performers while preserving the original motion, choreography, camera work, and location, on Seedance 2.5. Try free — pay per generation, no subscription.
Om denna modell
Seedance 2.5 Motion Control is the Seedance 2.5 version of Motion Control: it recasts an existing performance video with new performers while automatically preserving the source clip's motion, choreography, blocking, and camera work, and while keeping the original location intact. Upload a reference video plus character reference image(s) of the new performer(s) and an optional short instruction — the model extracts the motion/camera geometry and a clean background plate from your reference video, builds a multi-angle identity sheet from each character photo, and hands everything to Seedance 2.5 Omni Reference (720p) to render the recast.
Kostnadsanalys
| Leverantör | Kostnad | Anteckningar |
|---|---|---|
| muapiapp | Base 720p Omni Reference rate + preprocessing (depth + environment + per-character sheets) | En debiterad begäran omfattar hela pipelinen: djupextraktion, framtagning av ren bakgrundsplatta, generering av karaktärsblad och slutlig rendering av rollbytet. |
| Fal.ai | Inte tillgänglig | Ingen motsvarande pipeline för rörelsebaserat rollbyte i en enda begäran erbjuds — samma resultat skulle kräva att flera separata modeller kopplas samman manuellt. |
| Replicate | Inte tillgänglig | Replicate erbjuder ingen motsvarande pipeline för rörelsebaserat rollbyte i en enda begäran. |
En debiterad begäran omfattar hela pipelinen: djupextraktion, framtagning av ren bakgrundsplatta, generering av karaktärsblad och slutlig rendering av rollbytet.
Ingen motsvarande pipeline för rörelsebaserat rollbyte i en enda begäran erbjuds — samma resultat skulle kräva att flera separata modeller kopplas samman manuellt.
Replicate erbjuder ingen motsvarande pipeline för rörelsebaserat rollbyte i en enda begäran.
** Konkurrentens prissättning beräknas baserat på liknande modellarkitekturer och användningsnivåer.
Konfigurationsschema
| Parameter | Typ | Beskrivning | Standard |
|---|---|---|---|
| uppmaning | string | Optional short creative brief describing the recast, e.g. 'swap the two dancers with the people in the reference images'. If omitted, roles are inferred automatically from the reference video and images. | Swap the two dancers with the people in the reference images, keep the same room. |
| mål | string | Reference video whose motion, choreography, blocking, and camera work will be preserved. The original performers and location are automatically replaced. | https://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/seedance-v2.0-omni-reference.mp4 |
| Character måls | array | Character reference images — the new performers who will be recast into the video, in the order they should appear. | https://cdn.muapi.ai/assets/image_download_21.avif |
| bildförhållande | Enum (8 alternativ) | bildformat för utgående video. | 16:9 |
| Varaktighet (sekunder) | int | Video duration in seconds (4-30). | 5 |
| Frö | int | frö. -1. | 42 |
| Hög bithastighet | boolean | , . | false |
| Generera ljud | boolean | Generate audio (music/SFX) for the recast video. Off by default — a motion-control recast usually shouldn't have fabricated audio layered over the preserved performance. | false |
Optional short creative brief describing the recast, e.g. 'swap the two dancers with the people in the reference images'. If omitted, roles are inferred automatically from the reference video and images.
Swap the two dancers with the people in the reference images, keep the same room.Reference video whose motion, choreography, blocking, and camera work will be preserved. The original performers and location are automatically replaced.
https://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/seedance-v2.0-omni-reference.mp4Character reference images — the new performers who will be recast into the video, in the order they should appear.
https://cdn.muapi.ai/assets/image_download_21.avifbildformat för utgående video.
16:9Video duration in seconds (4-30).
5frö. -1.
42, .
falseGenerate audio (music/SFX) for the recast video. Off by default — a motion-control recast usually shouldn't have fabricated audio layered over the preserved performance.
falseUtvecklardokumentation
video_url) whose motion, choreography, blocking, and camera work should be preserved.images_list, up to 30) — each gets its own multi-angle identity sheet generated automatically before the final render.prompt describing the recast; if omitted, roles are inferred automatically from the video and images.aspect_ratio, duration (4-30s), seed, and high_bitrate if needed.generate_audio is off by default — the recast has no synthesized music/SFX unless explicitly enabled.Vanliga frågor
Motion, choreography, blocking, timing, and camera work (angle, framing, movement) are preserved. The original performers' identity, wardrobe, and colors are replaced, while the real filming location, architecture, and lighting are kept intact.
Yes — provide one character reference photo per performer in `images_list` (up to 30). Each photo gets its own automatically generated multi-angle identity sheet, so multiple performers can be swapped in a single request.
No, not by default. `generate_audio` defaults to false, since a motion-control recast is meant to preserve an existing performance rather than add fabricated music or sound effects. Set it to true to opt in.
Same recast pipeline (depth extraction, environment clean-plate, character sheets, structured prompt generation), built on Seedance 2.5 Omni Reference instead of 2.0 — supports up to 30 reference images (vs. 9), longer durations (up to 30s vs. 15s), and adds `seed`/`high_bitrate` controls.
Base generation cost is the same as Seedance 2.5 Omni Reference (720p rate x output duration, with a discounted combined rate when a reference video is used), plus internal preprocessing: depth extraction ($0.04/sec of the source video), an environment clean-plate pass (2 frames, $0.06 each), and one character-sheet generation per reference photo ($0.09 each).