---
title: Transforming and restyling video — Ray3.2 | Runware Docs
url: https://runware.ai/docs/models/luma-ray3-2/guides/editing-video
description: "How to transform footage with Luma Ray 3.2: restyle or reskin a clip while its motion carries through, using the strength dial and per-signal conditioning controls."
---
### [Introduction](https://runware.ai/docs/models/luma-ray3-2/guides/editing-video#introduction)

Ray 3.2 re-imagines footage you already have. You pass a clip and a prompt, and the model re-renders it guided by the source, **carrying the original motion and timing through into a new look**. It's a transformation tool, **not a surgical editor**: the prompt reinterprets the whole frame, so faces and backgrounds are reimagined along with the style rather than held pixel-for-pixel.

[Watch video](https://runware.ai/docs/assets/source-performer.DOfxSOto.mp4)

*Source*

[Watch video](https://runware.ai/docs/assets/output-hero-performance.BFdRVZNm.mp4)

*The same performance, reimagined as a figure of light*

The playing carries straight through while everything else is rebuilt from the prompt, and that is the model's sweet spot: bold transformations where **the performance is the throughline** and the new look is the point. Editing keeps the source aspect ratio, so changing format is a separate [reframing](https://runware.ai/docs/models/luma-ray3-2/guides/reframing-video) step. This guide covers the request, the `strength` dial that sets how far the result departs from the source, and the per-signal controls.

### [The request](https://runware.ai/docs/models/luma-ray3-2/guides/editing-video#the-request)

An edit is a normal video request with a source clip in `inputs.video` and a prompt describing the look you want. **The model follows the source's motion and composition**, and the prompt drives everything else.

**Request**:

```json
[
  {
    "taskType": "videoInference",
    "taskUUID": "e5d6c7b8-9a0b-1c2d-3e4f-5a6b7c8d9e0f",
    "model": "luma:ray@3.2",
    "positivePrompt": "Transform the violinist into a luminous figure of flowing golden light against a dark void, ribbons of light streaming from the bow and tracing his body, following his exact bowing and motion.",
    "inputs": {
      "video": "https://example.com/violinist.mp4"
    },
    "settings": {
      "edit": { "strength": "flex_2" }
    }
  }
]
```

**Response**:

```json
{
  "data": [
    {
      "taskType": "videoInference",
      "taskUUID": "e5d6c7b8-9a0b-1c2d-3e4f-5a6b7c8d9e0f",
      "videoUUID": "f6e5d4c3-b2a1-0987-6543-21fedcba0987",
      "videoURL": "https://vm.runware.ai/video/os/a14d18/ws/2/vi/f6e5d4c3-b2a1-0987-6543-21fedcba0987.mp4"
    }
  ]
}
```

`inputs.video` takes a URL or the UUID of a previous generation. Describe the target look and let the motion carry. The model rebuilds the rest of the frame from there.

### [Controlling how much changes](https://runware.ai/docs/models/luma-ray3-2/guides/editing-video#controlling-how-much-changes)

`settings.edit.strength` is the **preserve-versus-reinterpret dial**. It runs in three bands: `adhere` stays close to the source, `flex` takes moderate liberties, and `reimagine` treats the source as loose guidance. Each band has three levels (`adhere_1` through `reimagine_3`) for finer steps.

Below, one prompt turns the dolphin into a cyberpunk cybernetic creature, run at one level from each band against the source it started from:

[Watch video](https://runware.ai/docs/assets/source-dolphin.BzoYeSDX.mp4)

*Source*

[Watch video](https://runware.ai/docs/assets/output-strength-adhere.BhT4iETo.mp4)

*adhere_1: light circuitry, ocean intact*

> **Prompt**: Transform only the dolphin into a cyberpunk cybernetic creature: glowing neon circuitry and electric-blue light strips across its body, sleek dark cybernetic plating, holographic fins, while keeping the ocean, splash, and sky natural and photoreal.

[Watch video](https://runware.ai/docs/assets/output-strength-flex.BU4sLIwO.mp4)

*flex_2: brighter glow, scene shifting*

> **Prompt**: Transform only the dolphin into a cyberpunk cybernetic creature: glowing neon circuitry and electric-blue light strips across its body, sleek dark cybernetic plating, holographic fins, while keeping the ocean, splash, and sky natural and photoreal.

[Watch video](https://runware.ai/docs/assets/output-strength-reimagine.dsqJ_T1k.mp4)

*reimagine_3: full neon, scene reworked*

> **Prompt**: Transform only the dolphin into a cyberpunk cybernetic creature: glowing neon circuitry and electric-blue light strips across its body, sleek dark cybernetic plating, holographic fins, while keeping the ocean, splash, and sky natural and photoreal.

Each band sets how far the result departs from the source. At `adhere_1` the cyber-dolphin **stays locked to the real leap and the natural ocean**. At `reimagine_3` the model **reworks the creature and scene more freely**, keeping only a loose echo of the source.

```json
"settings": {
  "edit": { "strength": "reimagine_3" }
}
```

### [Per-signal controls](https://runware.ai/docs/models/luma-ray3-2/guides/editing-video#per-signal-controls)

For tighter command than a single dial, `settings.edit.controls` exposes the individual conditioning signals:

- `poseStrength` (`precise` or `coarse`) sets how strictly the subject's skeleton is followed.
- `depthBlur` and `normalsAugmentation` (both 0 to 1) loosen scene geometry and surface detail as they rise, granting more reinterpretation.
- `trajectorySparsity` (0 to 1) controls how many motion anchors hold the movement in place.
- `face` biases the result toward a recognizable face, though a heavy transform still reinterprets it.

The transformation below pins the dolphin's exact leap with `poseStrength` while applying the same cyberpunk transform:

[Watch video](https://runware.ai/docs/assets/output-controls.DNKhXRWz.mp4)

*Leap held with per-signal controls*

> **Prompt**: Transform only the dolphin into a cyberpunk cybernetic creature: glowing neon circuitry and electric-blue light strips across its body, sleek dark cybernetic plating, holographic fins, while keeping the ocean, splash, and sky natural and photoreal.

```json
"settings": {
  "edit": {
    "controls": { "poseStrength": "precise" }
  }
}
```

> [!NOTE]
> Set `settings.edit.autoControls` to `true` to let Ray derive the whole conditioning schedule from the source automatically. It's the fastest path when you don't want to tune signals by hand, and it can't be combined with `strength` or manual `controls`.

### [Changing the setting](https://runware.ai/docs/models/luma-ray3-2/guides/editing-video#changing-the-setting)

The same mechanism transforms the world around a shot. The source street below is reskinned into deep winter, the camera move carried through. As with any edit **the buildings are rebuilt rather than copied**, so reach for this when you want a fresh take on a setting, not the old one left untouched under new weather.

[Watch video](https://runware.ai/docs/assets/source-street.BVktj-Hy.mp4)

*Source*

[Watch video](https://runware.ai/docs/assets/output-environment.C25LX8k7.mp4)

*Reskinned to winter*

> **Prompt**: Turn this street into deep winter: snow blanketing the ground and rooftops, bare trees, a cold overcast sky and soft falling snow, keeping the street's overall layout and the camera move from the source.

Relighting a scene or restyling the subject runs the same way: describe the new look, then pick a `strength` for how far the result should travel from the source.

### [Tips](https://runware.ai/docs/models/luma-ray3-2/guides/editing-video#tips)

1. **Describe the look you want, not a precise edit.** Name the target style and let the motion carry. The model re-renders the rest, so don't count on faces or backgrounds staying untouched.
    
2. **Start low on the strength dial.** `adhere` and `flex` keep the shape and motion close. Reach for `reimagine` only when you want the model to rework the subject itself.
    
3. **Turn on `face` for people.** It biases the result toward a recognizable face, though a heavy transform will still reinterpret it.
    
4. **Let `autoControls` handle the first pass.** It derives the conditioning from the source, which is usually enough before you reach for manual signals.
    
5. **Reframe in a separate step.** Editing holds the source aspect ratio, so changing format is its own [reframing](https://runware.ai/docs/models/luma-ray3-2/guides/reframing-video) request rather than part of the edit.