---
title: Swap the actor and keep the performance
display: '*Swap* the actor and keep the performance'
nav_title: Swap the actor
summary:
  - "Make one neutral performance on a locked camera, then recast it with a brand mascot, a stylized character and a photoreal ambassador."
  - "Each recast is one still on the performer's spot plus one motion-control run."
  - "A key-pose check at five matching times picked the model; run the same check on every recast."
description: Make one reference performance, then have several characters perform exactly the same moves with a motion-control model, checked pose by pose.
section: playbooks
order: 146
type: playbook
topic: Film and animation
level: Build
roles: [artist, marketer]
time: { read: 10, do: 40, wait: 15 }
needs: ["Any plan with credits", "ffmpeg and ImageMagick for the checks (optional)"]
last_verified: 2026-10-16
models_checked: ["Kling V3 Pro - Motion Control", "Kling V3 Std - Motion Control", "Minimax H3 Max Recast", "Seedance 2.5", "Minimax H3", "GPT Image 2.5 Sunburst", "Cartwheel Mascot"]
related: [direct-the-camera-and-motion, restyle-footage-keep-the-motion, character-reference-sheet]
pdf: true
run_in: [model_kling-v3-pro-motion-control, model_minimax-h3-max-recast, model_bytedance-seedance-2-5, model_minimax-h3]
hero_in_header: true
# the use case made, on scenario.com/explorations, and the platform workflows that run it
made_with:
  - { slug: same-moves-new-actor, title: "Same Moves, New Actor" }
  - { slug: a-cast-of-one, title: "A Cast of One" }
thumb: playbooks/swap-the-actor-keep-the-performance/thumb.webp
video: tutorials/swap-the-actor-keep-the-performance.mp4
chapters:
  - { at: 0, title: "The performance to recast", image: "/media/images/playbooks/swap-the-actor-keep-the-performance/ch-01-the-performance-to-recast.webp" }
  - { at: 22.5, title: "A clean driving video starts with a clean still", image: "/media/images/playbooks/swap-the-actor-keep-the-performance/ch-02-a-clean-driving-video-starts-with-a-clean-still.webp" }
  - { at: 40.5, title: "The base take", image: "/media/images/playbooks/swap-the-actor-keep-the-performance/ch-03-the-base-take.webp" }
  - { at: 59, title: "One pattern, one character slot", image: "/media/images/playbooks/swap-the-actor-keep-the-performance/ch-04-one-pattern-one-character-slot.webp" }
  - { at: 87, title: "Pilot the hardest character", image: "/media/images/playbooks/swap-the-actor-keep-the-performance/ch-05-pilot-the-hardest-character.webp" }
  - { at: 104, title: "Score five key poses", image: "/media/images/playbooks/swap-the-actor-keep-the-performance/ch-06-score-five-key-poses.webp" }
  - { at: 130, title: "A face element for photoreal faces", image: "/media/images/playbooks/swap-the-actor-keep-the-performance/ch-07-a-face-element-for-photoreal-faces.webp" }
  - { at: 157, title: "Recap", image: "/media/images/playbooks/swap-the-actor-keep-the-performance/ch-08-recap.webp" }
steps:
  - title: "A clean driving video starts with a clean still"
    text: "Create › Images › GPT Image 2.5 Sunburst, Dimensions 16:9, Quality high. Motion transfer works best from a clean driving video, so the performer is invented for the job: one dancer, centered, with room all around her."
    prompt: |-
      Full-body photo of a dancer in a seamless pale sea-glass green photo studio, shot from a locked tripod at chest height, wide 16:9 frame. The dancer is an invented woman in her late twenties with short dark curly hair, wearing a plain white t-shirt, loose stone-grey sweatpants and white sneakers with no logos. She stands in a relaxed neutral stance facing the camera, arms loose by her sides, in the exact center of the frame. Her whole body from head to feet fills only about half of the frame height, with generous empty space above her head, below her feet and on both sides. Seamless pale sea-glass green backdrop curving into the floor, soft even studio light, a soft contact shadow under her feet. Photoreal, natural skin texture. No text, no logos, no other people.
  - title: "The base take"
    text: "Create › Videos › Minimax H3, the performer still as First Frame, Duration 5 s, Resolution 768P. List the moves in order, lock the camera and keep her hands below her head; whatever poses the take makes become the master every recast must match."
    prompt: |-
      The camera stays perfectly still on a locked tripod: no camera movement, no zoom, no cuts. The dancer performs a short upbeat standing routine facing the camera, staying on the same spot in the center of the frame: she sways her hips side to side, waves both arms at shoulder height twice, claps once in front of her chest, steps left and right on the beat, makes a quick half turn to her left and back to face the camera, and ends with both hands on her hips. Her hands never go above her head, and her whole body from head to feet stays inside the frame the whole time. Smooth real-time motion, natural human movement. Same plain pale sea-glass green studio, no other people, no text. Soft sound of sneakers on the studio floor and one clap, no music, no speech.
  - title: "One pattern, one character slot"
    text: "Create › Images › GPT Image 2.5 Sunburst, with the performer still in Reference Images as the layout. Only the character sentence changes; this is the lifeguard's, and the mascot also got the brand's can as a second reference, for its colors."
    prompt: |-
      Replace the woman in image 1 with a stylized 3D animated-feature character: a sturdy, cheerful lifeguard in his fifties with a big bushy grey mustache, sun-tanned skin, a short-sleeved coral lifeguard shirt with a plain white cross-free pocket, sea-glass green board shorts, a whistle on a cord around his neck and white canvas sneakers; hand-painted textures with soft stylized shading and appealing exaggerated proportions. The character stands exactly where she stands: in the center of the frame, feet on the floor at the same place, the same height in the frame from head to feet, facing the camera in the same relaxed neutral stance with arms loose by the sides and empty hands. Keep the seamless pale sea-glass green studio, the soft even light, the soft contact shadow and the camera exactly the same. Only one character, nobody else, no text, no logos.
  - title: "Pilot the hardest character"
    text: "Create › Videos › Kling V3 Pro - Motion Control: Character Image the wren still, Reference Video the base take, Character Orientation Video, Keep Original Sound off. The mascot goes first because it is the hardest (round body, wings for hands, no human face), and the same inputs also went to Minimax H3 Max Recast and Seedance 2.5."
    prompt: |-
      The plump sage-green wren mascot performs exactly the same dance as the woman in the video: the same moves in the same order with the same timing, on the same spot. Static locked-off camera, plain mint-green studio, the whole body always inside the frame. The mascot keeps its exact shape and colors in every frame, with its cream neckerchief and orange legs.
  - title: "Score five key poses"
    text: "Compare every take with the base take at the same five moments: 0.75, 1.5, 3.4, 4.2 and 5.0 s. Kling landed all five, Recast fell behind from 3 s and Seedance spread its wings at the clap, so Kling recast the lifeguard and the swimmer too."
  - title: "A face element for photoreal faces"
    text: "By the last second the swimmer's face had become another woman's, because a photoreal face is small in a full-body frame. Make a close-up from her cast still and pass it to Kling as an element named in the prompt."
    prompt: |-
      Head-and-shoulders close-up portrait of the same woman as in image 1: the same invented woman in her seventies with chin-length wavy silver hair, the same face, the same small pearl earrings if any, the same sage-green linen shirt collar. She faces the camera with the same friendly closed-mouth smile, in the same soft even studio light against the same plain mint-green background. Keep her face exactly the same as in image 1. No text, no logos.
agent_steps:
  - title: "Connect the Scenario MCP"
    text: "Connect your agent and sign in once at [mcp.scenario.com](https://mcp.scenario.com). Then tell it which Scenario team and project to use, so every file lands there."
  - title: "Give the agent the files"
    text: "Nothing to upload for the performer: the agent generates her, so the driving video is clean. For the mascot, upload the brand's can with upload_asset or give its asset ID: it is the mascot's second reference, for its colors."
  - title: "Brief the agent: the performer and the base take"
    text: "Whatever poses the base take makes become the master every recast must match, so the moves are listed in order and the camera is locked."
    prompt: |-
      Make the performer still with GPT Image 2.5 Sunburst (model_openai-gpt-image-2-5-sunburst), 16:9, quality "high". Prompt, word for word:
      Full-body photo of a dancer in a seamless pale sea-glass green photo studio, shot from a locked tripod at chest height, wide 16:9 frame. The dancer is an invented woman in her late twenties with short dark curly hair, wearing a plain white t-shirt, loose stone-grey sweatpants and white sneakers with no logos. She stands in a relaxed neutral stance facing the camera, arms loose by her sides, in the exact center of the frame. Her whole body from head to feet fills only about half of the frame height, with generous empty space above her head, below her feet and on both sides. Seamless pale sea-glass green backdrop curving into the floor, soft even studio light, a soft contact shadow under her feet. Photoreal, natural skin texture. No text, no logos, no other people.

      When I approve it, animate it with Minimax H3 (model_minimax-h3): firstFrameImage set to the still, duration 5, resolution "768P". Prompt, word for word:
      The camera stays perfectly still on a locked tripod: no camera movement, no zoom, no cuts. The dancer performs a short upbeat standing routine facing the camera, staying on the same spot in the center of the frame: she sways her hips side to side, waves both arms at shoulder height twice, claps once in front of her chest, steps left and right on the beat, makes a quick half turn to her left and back to face the camera, and ends with both hands on her hips. Her hands never go above her head, and her whole body from head to feet stays inside the frame the whole time. Smooth real-time motion, natural human movement. Same plain pale sea-glass green studio, no other people, no text. Soft sound of sneakers on the studio floor and one clap, no music, no speech.

      Remove the sound from the take before it is used as the driving video. Quote each run with a dry run first and wait for my go.
  - title: "Brief the agent: the cast stills"
    prompt: |-
      Make one cast still per character with GPT Image 2.5 Sunburst, with the performer still in referenceImages as an array (for the mascot, add the brand's can as a second reference). Only the character sentence changes. The lifeguard's prompt, word for word:
      Replace the woman in image 1 with a stylized 3D animated-feature character: a sturdy, cheerful lifeguard in his fifties with a big bushy grey mustache, sun-tanned skin, a short-sleeved coral lifeguard shirt with a plain white cross-free pocket, sea-glass green board shorts, a whistle on a cord around his neck and white canvas sneakers; hand-painted textures with soft stylized shading and appealing exaggerated proportions. The character stands exactly where she stands: in the center of the frame, feet on the floor at the same place, the same height in the frame from head to feet, facing the camera in the same relaxed neutral stance with arms loose by the sides and empty hands. Keep the seamless pale sea-glass green studio, the soft even light, the soft contact shadow and the camera exactly the same. Only one character, nobody else, no text, no logos.

      Quote first and wait for my go. Show me each still next to the performer still: the character must stand on the same spot, at the same height in the frame.
  - title: "Pilot the hardest character, then recast"
    text: "The mascot goes first: round body, wings for hands, no human face. Kling landed all five key poses; Recast fell behind from 3 s and Seedance spread its wings at the clap."
    prompt: |-
      Recast the wren mascot with Kling V3 Pro - Motion Control (model_kling-v3-pro-motion-control): image set to the wren still, video set to the silent base take, characterOrientation "video", keepOriginalSound false. Prompt, word for word:
      The plump sage-green wren mascot performs exactly the same dance as the woman in the video: the same moves in the same order with the same timing, on the same spot. Static locked-off camera, plain mint-green studio, the whole body always inside the frame. The mascot keeps its exact shape and colors in every frame, with its cream neckerchief and orange legs.

      Compare it with the base take at 0.75, 1.5, 3.4, 4.2 and 5.0 s and tell me whether the pose matches at each moment. If it does, recast the lifeguard and the swimmer the same way, in parallel with wait: false and one jobs_wait, with the same prompt and only the character and costume sentence changed. Quote each run first and wait for my go.
  - title: "Hold the photoreal face"
    text: "By the last second the swimmer's face had become another woman's: a photoreal face is small in a full-body frame. Accept when every key pose matches, the feet stay on the spot, the camera does not move, and costume and face hold to the last frame."
    prompt: |-
      Make a close-up of the swimmer with GPT Image 2.5 Sunburst, with her cast still as the reference. Prompt, word for word:
      Head-and-shoulders close-up portrait of the same woman as in image 1: the same invented woman in her seventies with chin-length wavy silver hair, the same face, the same small pearl earrings if any, the same sage-green linen shirt collar. She faces the camera with the same friendly closed-mouth smile, in the same soft even studio light against the same plain mint-green background. Keep her face exactly the same as in image 1. No text, no logos.

      Then rerun her Kling recast with elements set to [{frontalImage: the close-up, referenceImages: [her cast still]}] and name @Element1 in the prompt. Quote it first and wait for my go.
  - title: "File and report"
    prompt: |-
      Create a collection for this dance with the performer still, the base take, the three cast stills and the three kept recasts. Report the models, every asset ID, the key-pose scores of each recast and the total cost spent.
updated: 2026-10-16
canonical: https://learn.scenario.com/playbooks/swap-the-actor-keep-the-performance
---

Last updated: 2026-10-16

# Swap the actor and keep the performance

> Make one reference performance, then have several characters perform exactly the same moves with a motion-control model, checked pose by pose.

In short:

- Make one neutral performance on a locked camera, then recast it with a brand mascot, a stylized character and a photoreal ambassador.
- Each recast is one still on the performer's spot plus one motion-control run.
- A key-pose check at five matching times picked the model; run the same check on every recast.


Saltwren, an invented sparkling sea-water brand, wants one short dance for its launch spots, performed by three faces of the brand. One invented dancer performs a 5-second routine on a locked camera. Three characters then perform exactly her moves: the Saltwren wren mascot, a stylized lifeguard and a photoreal swimmer in her seventies.

:::note As of October 2026
The models, settings and screens in this article are the ones Scenario offered in October 2026. New models and updates arrive often, so check the app for newer options before you choose.
:::

:::video https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/95a79e18848ccb3ffbce643b83f5d5bb91ed81a5735b94b55432acd4376e4318.mp4
The base take (top left) and three recasts with Kling V3 Pro - Motion Control: the wren mascot, the lifeguard and the swimmer. Same 124 frames, same camera, same moves.
:::

## The brief

| Field | Brief |
|---|---|
| Goal | One reference performance, recast with three characters doing the same moves |
| Performance | 5 seconds: arms out, arms up, clap, half turn, hands on hips |
| Format | 16:9, 1344x768, 24 fps, 124 frames, the base take's own size and length |
| Fixed | Locked camera, framing, the performer's spot, every move and its timing, the sea-glass green studio and light |
| Changes | The character only: the wren mascot, a stylized lifeguard in his fifties, a photoreal former open-water swimmer in her seventies |
| Accept when | Every key pose lands at the same time as in the base take; the whole body stays in frame; design and face hold to the last frame |

## Approach

:::flow
Base take | performer still, Minimax H3, locked camera | video
Cast stills | same spot, height and stance | image
Shoot-out | three models on the mascot | video
Recasts | Kling V3 Pro - Motion Control | video
Track check | five key poses, matching times |
:::

Motion transfer works best from a clean driving video: one performer, a locked camera, the whole body in frame, hands no higher than the head. So the performance is made for the job.

The driving video sets every move and its timing, the camera, the framing and the spot; the character still sets the design, face and costume, drawn on the performer's spot at her size and in her stance.

- **Model used:** Kling V3 Pro - Motion Control, the shoot-out winner: five of five key poses on time.
- **Alternative:** Seedance 2.5 in reference mode landed four of five and kept the full body in frame, but it took longer. Minimax H3 Max Recast, the most recent replace model, kept the design but fell behind from 3 seconds on, at more than twice the price. Cartwheel Mascot, the top recommendation for mascot swaps in October 2026, costs many times more per clip; not tested.

![Two inputs feed Kling V3 Pro - Motion Control, the shoot-out winner. The driving video, the base take, controls every move and its timing, the camera, the framing and the spot. The character still controls the design, the face and the costume, drawn at the performer's size and stance. The result is a recast: the same moves with a new character, its key poses landing at the same times as in the base take. Start every still on the performer's spot, so the model only has to move the character.](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/08d3802d43eb6d82d09952581ba554de05bcab96780d6c8a983bef7e0c20e473.svg "The driving video gives the moves, the still gives the look.")

## Steps

:::steps
1. **Make the performer still.** **Create** > **Images**, **Model** GPT Image 2.5 Sunburst, **Dimensions** 16:9 (2048x1152), **Quality** high, two takes, 32 seconds. The studio color is the brand's sea-glass green, so every recast sits in the same world.

   ```prompt
   Full-body photo of a dancer in a seamless pale sea-glass green photo studio,
   shot from a locked tripod at chest height, wide 16:9 frame. The dancer is an
   invented woman in her late twenties with short dark curly hair, wearing a
   plain white t-shirt, loose stone-grey sweatpants and white sneakers with no
   logos. She stands in a relaxed neutral stance facing the camera, arms loose by
   her sides, in the exact center of the frame. Her whole body from head to feet
   fills only about half of the frame height, with generous empty space above her
   head, below her feet and on both sides. Seamless pale sea-glass green backdrop
   curving into the floor, soft even studio light, a soft contact shadow under her
   feet. Photoreal, natural skin texture. No text, no logos, no other people.
   ```

2. **Make the base take** ([Animate from a first frame](https://learn.scenario.com/browse)). **Create** > **Videos**, **Model** Minimax H3, the still as **First Frame**, **Duration** 5 s, **Resolution** 768P. 3 minutes 12 seconds. List the moves in order; keep the hands no higher than the head.

   ```prompt
   The camera stays perfectly still on a locked tripod: no camera movement, no
   zoom, no cuts. The dancer performs a short upbeat standing routine facing the
   camera, staying on the same spot in the center of the frame: she sways her
   hips side to side, waves both arms at shoulder height twice, claps once in
   front of her chest, steps left and right on the beat, makes a quick half turn
   to her left and back to face the camera, and ends with both hands on her hips.
   Her hands never go above her head, and her whole body from head to feet stays
   inside the frame the whole time. Smooth real-time motion, natural human
   movement. Same plain pale sea-glass green studio, no other people, no text.
   Soft sound of sneakers on the studio floor and one clap, no music, no speech.
   ```

   The take read the routine its own way: arms out, arms up to head height, a clap, a turn that shows her back, and hands on hips. That is fine: the base take is the master, and its own poses are what every recast must match. Then remove the sound: `ffmpeg -i base.mp4 -an -c:v copy base-silent.mp4`.

3. **Make one cast still per character** ([Give each reference a role](https://learn.scenario.com/browse)). The performer still in **Reference Images** is the layout; the prompt is the character. About 33 seconds each, in parallel. One pattern, one slot:

   ```prompt
   Replace the woman in image 1 with [CHARACTER]. The character stands exactly
   where she stands: in the center of the frame, feet on the floor at the same
   place, the same height in the frame from head to feet, facing the camera in
   the same relaxed neutral stance with arms loose by the sides and empty hands.
   Keep the seamless pale sea-glass green studio, the soft even light, the soft
   contact shadow and the camera exactly the same. Only one character, nobody
   else, no text, no logos.
   ```

   The three character slots, as run. The mascot takes a second reference, the brand's can shot, for the wren mark and colors; its prompt adds "Use image 2 only for the wren mark and the brand colors, not for the cans" and ends with "no cans".

   ```prompt
   the Saltwren brand mascot: a plump, round little sea wren bird character
   standing upright, based on the small wren mark printed on the cans in image 2,
   with soft sea-glass green and cream feathers, a short perky tail, round dark
   eyes with white highlights, a tiny pale coral beak, small wings that work like
   hands, short orange legs with three-toed feet, and a little cream neckerchief;
   stylized 3D cartoon render with soft materials

   a stylized 3D animated-feature character: a sturdy, cheerful lifeguard in his
   fifties with a big bushy grey mustache, sun-tanned skin, a short-sleeved coral
   lifeguard shirt with a plain white cross-free pocket, sea-glass green board
   shorts, a whistle on a cord around his neck and white canvas sneakers;
   hand-painted textures with soft stylized shading and appealing exaggerated
   proportions

   a photoreal brand ambassador: an invented woman in her early seventies, a
   former open-water swimmer, with a short silver bob, light olive skin with
   natural wrinkles and freckles, a warm closed-mouth smile, wearing a loose
   sea-glass green linen shirt and matching wide linen trousers and white canvas
   sneakers; live-action commercial photography
   ```

   The wren came back shorter than the performer, as a small bird should. Accepted: the motion model sizes the character from the still and the video together, and the check in step 5 decides.

   ![The performer and the three cast stills on the same spot](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/774d432a5b80a813c5f978081277e546468472c30f5efb9f954520cc312b50c3.webp "Performer still (top left) and the three cast stills: wren mascot, lifeguard, swimmer.")

4. **Run a shoot-out on the hardest character** ([Pilot the hardest case](https://learn.scenario.com/browse)). The mascot: round body, wings for hands, no human face. Same base take, same still, three models ([Use a video as the motion source](https://learn.scenario.com/browse)): Kling V3 Pro - Motion Control; Minimax H3 Max Recast at 768P; Seedance 2.5 in reference mode at 480p.

   ```prompt
   The plump sage-green wren mascot performs exactly the same dance as the woman
   in the video: the same moves in the same order with the same timing, on the
   same spot. Static locked-off camera, plain mint-green studio, the whole body
   always inside the frame. The mascot keeps its exact shape and colors in every
   frame, with its cream neckerchief and orange legs.
   ```

   For Seedance, the same sentences name the inputs: "@image1 is the character" and "the woman in @video1", plus "with the same full-body framing" and "No music, no speech".

5. **Score five key poses** ([Review with a score](https://learn.scenario.com/browse)). Pick moments with a clear pose in the base take: arms out (0.75 s), arms up (1.5 s), clap (3.4 s), back to camera mid-turn (4.2 s), hands on hips (5.0 s). Export them from every take and compare.

   ```bash
   for t in 0.75 1.5 3.4 4.2 5.0; do ffmpeg -ss $t -i take.mp4 -frames:v 1 pose-$t.png; done
   ```

   ![Five key moments for the dancer, Kling, Recast and Seedance: Recast still has its wings up at the clap and faces front at the turn; Seedance spreads its wings instead of clapping](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/9483cabe4bdcda206716c1134770d046557e0d3e6bbb90950ce41f9a7433d7c0.webp "Rows: base take, Kling, Recast, Seedance. Columns: 0.75, 1.5, 3.4, 4.2, 5.0 s.")

6. **Recast the other two with the winner,** Kling V3 Pro - Motion Control. The cast still is the character image, the silent base take the motion video; character orientation from the video, original sound off. Same prompt, new character and costume sentence. 3 minutes 56 seconds and 3 minutes 28 seconds, in parallel. This model ran through the Scenario MCP; its web panel labels were not checked.

7. **Repair the face that drifted** ([Repair at the cheapest stage](https://learn.scenario.com/browse)). Every pose landed, but by the last second the swimmer's face had narrowed into another woman's: a photoreal face is small in a full-body frame. The stylized lifeguard held. Make a close-up from the cast still (33 seconds) and pass it to Kling as an element.

   ```prompt
   Head-and-shoulders close-up portrait of the same woman as in image 1: the same
   invented woman in her seventies with chin-length wavy silver hair, the same
   face, the same small pearl earrings if any, the same sage-green linen shirt
   collar. She faces the camera with the same friendly closed-mouth smile, in the
   same soft even studio light against the same plain mint-green background. Keep
   her face exactly the same as in image 1. No text, no logos.
   ```

   The element takes the close-up as its frontal image and the full-body still as its reference image. Add one sentence to the prompt: "Her face is the face of @Element1 in every frame: the same woman in her seventies with wavy silver hair." The re-run took 3 minutes 26 seconds, at the same price. The face held to the last frame.

   ![The close-up element and the cast still, then the face at 0.1, 2.4 and 5.0 seconds without (top) and with (bottom) the element](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/681fd9fb47d061a8e271d7f8b577f5d15728a970992cb418d343e542e9dd4a8a.webp "Left: the close-up and the cast still. Top: first run, the face narrows by 5.0 s. Bottom: with the element, the same woman to the end.")

8. **Conform and pair** ([Conform clips before the edit](https://learn.scenario.com/browse)). Kling returns 1920x1088 at 30 fps; the base take is 1344x768 at 24 fps, both 5.17 seconds. Match the base take, then stack:

   ```bash
   ffmpeg -i recast.mp4 -vf "scale=1344:768:force_original_aspect_ratio=increase,crop=1344:768,fps=24" -frames:v 124 -an recast-1344.mp4
   ffmpeg -i base-1344.mp4 -i recast-1344.mp4 -filter_complex hstack -an side-by-side.mp4
   ```

   Seedance returned 121 frames at 480p; pad its last frame (`tpad=stop_mode=clone:stop=3`) so every take has 124.
:::

**With the Scenario MCP:** `model_run` on `model_kling-v3-pro-motion-control` with `image` (cast still), `video` (silent base take), `characterOrientation: "video"`, `keepOriginalSound: false`.

For the face, add `elements: [{frontalImage: closeUp, referenceImages: [castStill]}]` and name `@Element1` in the prompt. Each run cost what its `dry_run: true` quote said, with or without the element.


## Check the result

:::check
**Accept when:** at each key moment the character holds the base take's pose; the feet stay on the same spot; the whole body stays in frame; the camera does not move; costume and face hold to the last frame.
**Reject when:** a pose arrives late or early; the camera reframes; a limb leaves the frame; the face or costume changes mid-clip; a second character appears.
:::

| Shoot-out on the mascot | Kling V3 Pro - Motion Control | Minimax H3 Max Recast, 768P | Seedance 2.5, 480p |
|---|---|---|---|
| Key poses on time | 5 of 5 | 2 of 5, late from 3 s | 4 of 5, no clap |
| Framing | locked, full body | locked, full body | locked, full body, mascot drawn larger |
| Mascot design | held | held | held |
| Motion rhythm (correlation with the base) | 0.85 | 0.24 | 0.82 |
| Wait | 4 min 23 s | 1 min 23 s | 5 min 55 s |

The rhythm row follows the tempo and gives Seedance almost the same score as Kling, though it misses the clap; the key poses decided.

| Final recasts | Wren mascot | Lifeguard | Swimmer |
|---|---|---|---|
| Key poses on time | 5 of 5 | 5 of 5 | 5 of 5 |
| Design and face to the last frame | held | held | held with the face element |
| Camera lock (background change, max) | 0.47% | 0.56% | 0.53% |

Camera lock compares the left and right 12% of each frame with frame 0; the base take itself scored 0.41%.

![Five key moments for the dancer, the wren mascot, the lifeguard and the swimmer: the same pose in each column](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/e4fc75182c9b8148fae1d29867cac8829cff9477a2916ee0e805eafac0900e36.webp "Key poses at 0.75, 1.5, 3.4, 4.2 and 5.0 s.")

:::video https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/c2c4474a57e01db530166e257baac81d99f161caf06d30d055cdc9177876de64.mp4
Base take (left) and the swimmer recast with the face element (right), conformed to 1344x768, 24 fps, 124 frames, shown at 1280 wide.
:::

:::quiz Check yourself
? Key poses at 0.75, 1.5, 3.4, 4.2 and 5.0 seconds: the base take on top, then three takes of the wren mascot. Which take passes the brief?
![A grid of key poses: the dancer on the top row, then three rows of the wren mascot at the same five moments](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/beacef840f8449d65ab844959fa8468ae2ee63f555cc5fcb00a4d6154f58f8db.webp "Rows from the top: base take, Take A, Take B, Take C")
- [ ] Take A: four of five poses land and the body stays in frame, close enough for a 5-second clip
- [x] Take B: every pose matches the base take's column, full body, camera locked
- [ ] Take C: the mascot design holds in every frame, so it passes
> Every key pose has to land at the same time as in the base take. Take A spreads its wings where the dancer claps; Take C still has its wings up at the clap and faces front at the turn.

? In the swimmer recast, every pose lands on time, but by the last second her face belongs to another woman. What do you do?
- [ ] Accept it: the moves are what the brief fixes
- [x] Make a face close-up from the cast still and pass it as an element, with the full-body still as its reference image
- [ ] Run the same settings again until a take keeps the face
> Design and face must hold to the last frame. A close-up element named in the prompt kept the same woman to the end.
:::

## Make it repeatable

- **Keep the base take as the master.** A new character is one cast still and one transfer away.
- **Template the cast still** ([Batch from a template](https://learn.scenario.com/browse)): fixed pattern, one character slot.
- **Build it as a workflow** ([Package it as a workflow or skill](https://learn.scenario.com/browse)). In the **Node Editor**: a **Video** node for the base take, a **Text** node with the character sentences, **Split Text**, a **Loop** (its **Input List** port), an **Image Generator** on GPT Image 2.5 Sunburst with the performer still, a **Video Generator** on Kling V3 Pro - Motion Control, and an **Approval** after the first character.
- **Store the five key moments with the base take,** so every review checks the same frames.
- **Plan the element for photoreal faces.** In this run and the previous test, the photoreal character was the one whose face drifted; the stylized ones held.
- **Iterate on the cheaper tier.** Kling V3 Std - Motion Control quoted about three quarters of the Pro price for this clip; run finals on Pro.


## Runs and time

| Step | Runs | Kept | Wait |
|---|---|---|---|
| Performer still, two takes | 1 | 1 | 32 s |
| Base take, 5 s, 768P | 1 | 1 | 3 min 12 s |
| Cast stills | 3 | 3 | about 33 s, in parallel |
| Shoot-out on the mascot | 3 | 1 (Kling) | 1 min 23 s to 5 min 55 s, in parallel |
| Lifeguard and swimmer recasts | 2 | 1 (swimmer rejected) | 3 min 56 s, in parallel |
| Face close-up | 1 | 1 | 33 s |
| Swimmer with the face element | 1 | 1 | 3 min 26 s |
| Conform, checks, pairs (local) | 0 | n/a | seconds |

About 18 minutes of waiting. The video runs are almost all of the cost; more than half went to the two shoot-out losers and the rejected swimmer take.

The price shows on the **Generate** button before you run; with the Scenario MCP, ask for a dry-run quote.

## Variations

- **Brand:** the mascot in a seasonal costume, from the same base take.
- **Games:** an emote set for non-player characters: one performer take per emote, any number of characters.
- **Learning:** a presenter's gesture take reused by a course mascot.
- **Sound:** keep the original sound with Kling's sound option, or add music after the conform.
- **Same performer, new look:** restyle the clip instead of recasting it. See [Restyle footage, keep the motion](https://learn.scenario.com/playbooks/restyle-footage-keep-the-motion.md).
- **Your own take:** a phone video of you acting it out is a valid driving video. See [Direct the camera and motion](https://learn.scenario.com/video/direct-the-camera-and-motion.md).

## If it breaks

- **Poses arrive late.** Use a motion-control model and keep the clip short.
- **The camera reframes.** Reference-video models may build a new shot: use a motion-transfer model and write "static locked-off camera".
- **Hands leave the frame.** Keep the hands no higher than the head in the base take, and leave room around the performer.
- **A face drifts.** Add a face close-up as an element, with the full-body still as its reference image, and name it in the prompt.
- **An element run fails at once.** In the v6 test, an element with a frontal image alone failed; adding the full-body still as a reference image fixed it.
- **Proportions break.** Pilot the most different character first, and place its still on the performer's spot.

Source: https://learn.scenario.com/playbooks/swap-the-actor-keep-the-performance