---
title: Seedance 2.0 Fast | Runware Docs
url: https://runware.ai/docs/models/bytedance-seedance-2-0-fast
description: Faster multimodal video generation tuned for latency and iteration speed
---
# Seedance 2.0 Fast

![Seedance 2.0 Fast](https://assets.runware.ai/covers/bytedance-seedance-2-0-fast.jpg)

Seedance 2.0 Fast is a speed-optimized variant of ByteDance's unified multimodal audio-video generation model. It accepts text, image, audio, and video inputs in combination, like Seedance 2.0, but targets shorter wall-clock times and higher throughput for iterative workflows. It produces multi-shot videos with dual-channel synchronized audio including dialogue, ambient sound, and effects, with physics-aware motion and editing controls, while prioritizing responsiveness over the last increment of visual refinement so teams can preview and ship ideas faster.

- **Status**: live
- **ID**: `bytedance:seedance@2.0-fast`
- Try in Playground
- **Creator**: ByteDance
- **Release Date**: April 3, 2026
- **Capabilities**: Text to Video, Image to Video, Video to Video, Audio to Video, Edit, Extend, Checkpoint, Audio

## Pricing

$0.06 from, per second · ~2m 1s per request

**Rates** (per second)

- 480p: `$0.06`
- 720p: `$0.13`
- 720p · video to video: `$0.167`

**4 example generations**

- [first-last-frame](https://runware.ai/docs/models/bytedance-seedance-2-0-fast/examples#example-wheelchair-fencing-arena-background-swap) · 480p · 8s · audio: `$0.485` (~1m 45s)
- [first-frame](https://runware.ai/docs/models/bytedance-seedance-2-0-fast/examples#example-alpaca-ranch-background-replacement) · 720p · 5s: `$0.653` (~2m 17s)
- [text-to-video](https://runware.ai/docs/models/bytedance-seedance-2-0-fast/examples#example-subsea-drone-background-replacement) · 1470×630 · 6s · audio: `$0.787` (~1m 34s)
- [reference-to-video](https://runware.ai/docs/models/bytedance-seedance-2-0-fast/examples#example-counterfeit-currency-docuseries-titles) · 720p · 10s · audio: `$1.29` (~4m 12s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

Either provide `inputs.frameImages`, `inputs.referenceImages`, or `inputs.referenceVideos`, or specify `width/height`.

---

Inside `inputs`, `frameImages` cannot be used with `referenceImages` or `referenceVideos`.

---

When `inputs.referenceAudios` is provided, `inputs.frameImages`, `inputs.referenceImages`, or `inputs.referenceVideos` is required.

---

`resolution` cannot be used with `width/height`.

---

When `resolution` is provided, `inputs.frameImages`, `inputs.referenceImages`, or `inputs.referenceVideos` is required.

---

`width` and `height` must be used together.

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `480p (16:9)` | `864x496` |
| `480p (4:3)` | `752x560` |
| `480p (1:1)` | `640x640` |
| `480p (3:4)` | `560x752` |
| `480p (9:16)` | `496x864` |
| `480p (21:9)` | `992x432` |
| `720p (16:9)` | `1280x720` |
| `720p (4:3)` | `1112x834` |
| `720p (1:1)` | `960x960` |
| `720p (3:4)` | `834x1112` |
| `720p (9:16)` | `720x1280` |
| `720p (21:9)` | `1470x630` |

## Notes

Seedance 2.0 Fast supports multiple generation modes:

- **Text-to-Video:** Provide a prompt with `width`/`height`.
- **Image-to-Video:** Provide frame images via `inputs.frameImages` (up to 2, first/last). Dimensions are optional and inherited from the image if not specified.
- **Reference-Guided:** Provide reference images (`inputs.referenceImages`, up to 9) and/or reference videos (`inputs.referenceVideos`, up to 3) for visual guidance.
- **Audio-Guided:** Provide reference audios (`inputs.referenceAudios`, up to 3) to guide audio generation. Requires at least one reference image or reference video.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-outputformat)

- **Type**: `string`
- **Default**: `MP4`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`MP4\`: Widely supported video container (H.264), recommended for general use.
- \`WEBM\`: Optimized for web delivery.
- \`MOV\`: QuickTime format, common in professional workflows (Apple ecosystem).

**Allowed values**: `MP4` `WEBM` `MOV`

### [outputQuality](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-deliverymethod)

- **Type**: `string`
- **Default**: `async`

Determines how the API delivers task results.

**Allowed values**:

- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse. Required for long-running tasks like video generation.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (2 properties)`

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time.

#### [mode](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-safety-mode)

- **Path**: `safety.mode`
- **Type**: `string`
- **Default**: `fast`

Safety checking mode for video generation.

**Allowed values**:

- `fast` Checks key frames.
- `full` Checks all frames.

### [ttl](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [referenceImages](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `9`

List of reference images (UUID, URL, Data URI, or Base64).

### [frameImages](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `1`
- **Max items**: `2`

An array of frame-specific image inputs to guide video generation. Each item can be either a plain image input (UUID, URL, Data URI, or Base64) or an object that pairs an image with a target position in the video.

The `frameImages` parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. Position can be specified using `frame` (named positions or frame indices) or `timestamp` (seconds), depending on model support. This is different from `referenceImages`, which provide overall visual guidance without constraining specific timeline positions.

When the `frame` parameter is omitted, automatic distribution rules apply:

- **1 image**: Used as the first frame.
- **2 images**: First and last frames.

**Examples**:

**Shorthand format:** When you don't need to specify a frame position, you can pass a plain image input directly.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402"
]
```

**Object format:** When you need to specify a position, use an object with `image` and either `frame` or `timestamp` (model-dependent).

```json
"frameImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "frame": "first"
  }
]
```

**First and last frames:** With two images, they automatically become the first and last frames of the video sequence. You can mix shorthand and object formats.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402",
  {
    "image": "3ad204c3-a9de-4963-8a1a-c3911e3afafe",
    "frame": "last"
  }
]
```

**Format 1: string[]**:

- **Type**: `string`

Image input (UUID, URL, Data URI, or Base64).

**Format 2: object[]**:

#### [image](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-inputs-frameimages-format-2-image)

- **Path**: `inputs.frameImages.image`
- **Type**: `string`
- **Required**: true

Image input (UUID, URL, Data URI, or Base64).

#### [frame](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-inputs-frameimages-format-2-frame)

- **Path**: `inputs.frameImages.frame`
- **Type**: `object`

Target frame position for the image. Supports first and last frame.

**Allowed values**:

- `first` First frame of the video.
- `last` Last frame of the video.
- `0` Frame index 0 (first frame).
- `-1` Frame index -1 (last frame).

### [referenceVideos](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-inputs-referencevideos)

- **Path**: `inputs.referenceVideos`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `3`
- **Size (each)**: `300 px to 6000 px`
- **Aspect ratio (each)**: `1:2.5 to 2.5:1`

List of reference videos (UUID or URL).

### [referenceAudios](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-inputs-referenceaudios)

- **Path**: `inputs.referenceAudios`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `3`
- **Duration (each)**: `2s to 15s`

List of reference audios (UUID or URL).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `bytedance:seedance@2.0-fast`

Identifier of the model to use for generation.

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `10000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [width](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages and inputs.referenceImages and inputs.referenceVideos are not provided
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages and inputs.referenceImages and inputs.referenceVideos are not provided
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [resolution](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-resolution)

- **Type**: `string`
- **Default**: `720p`

Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input.

**Allowed values**: `480p` `720p`

### [duration](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-duration)

- **Type**: `integer`
- **Min**: `4`
- **Max**: `15`
- **Default**: `5`

Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [audio](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#request-settings-audio)

- **Path**: `settings.audio`
- **Type**: `boolean`
- **Default**: `true`

Generate synchronized audio.

## Response Parameters

### [taskType](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [videoUUID](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#response-videouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#response-videourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#response-videodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output video.

### [seed](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [NSFWContent](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/bytedance-seedance-2-0-fast#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-video (text-to-video)

[Watch video](https://assets.runware.ai/examples/bytedance-seedance-2-0-fast/a0f667dd-b21a-42c0-a29f-c36715cf8a17.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "09c47ac3-0f17-46ef-8087-15135c0e16a3",
  "model": "bytedance:seedance@2.0-fast",
  "positivePrompt": "Create a finished 6-second ultra-wide background-replacement shot for a marine robotics trade-show display. The isolated hero subject is a compact professional subsea inspection ROV: boxy yellow pressure housing, black tubular frame, two small lateral thrusters, forward camera dome, work lights, manipulator claw and a thin tether exiting behind it. Keep the ROV's proportions, surface details and silhouette perfectly stable throughout, with clean natural edges around the frame, claw, tether and spinning propellers. Replace its original studio background completely with a realistic underwater offshore wind-turbine inspection site in the North Sea. The ROV hovers beside the immense submerged steel monopile, with a visible bolted access panel, marine growth, drifting particles and distant structural cables fading into deep teal water. Its work lights cast narrow warm beams across the monopile while soft cyan daylight filters down from far above. Compose for 1470x630 panoramic landscape: ROV in the left-center third, facing right, with ample open water and turbine structure extending across the frame; no text, logos, borders or interface elements. One continuous shot with restrained documentary realism. Begin nearly static for the first second, then the ROV glides slowly right as its thrusters spin and the manipulator makes one small corrective movement. Camera performs a smooth lateral tracking move at matching speed with subtle underwater inertia, creating gentle background parallax while the subject remains crisp and prominent. Fine bubbles and suspended sediment drift past at different depths; the tether responds naturally to water resistance. End on a stable inspection position as the work lights sweep over the access panel. Photorealistic marine cinematography, cool navy and oxidized teal palette with safety-yellow contrast, realistic underwater falloff, no fantasy creatures. Synchronized sound: low muffled electric thruster hum rising during the glide, soft propeller wash, sparse bubbles, faint tether creak and a subdued metallic underwater resonance as the light crosses the turbine panel; no music and no speech.",
  "width": 1470,
  "height": 630,
  "duration": 6,
  "settings": {
    "audio": true
  }
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/bytedance-seedance-2-0-fast/89dc3f21-5e15-40ad-bbb7-fcfbf633e76b.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "0362c351-5d82-4a42-af84-90194d6c4738",
  "model": "bytedance:seedance@2.0-fast",
  "positivePrompt": "A polished five-second breeder profile film featuring the same champion white suri alpaca with the distinctive caramel patch around its left eye, now standing in a vast high-altitude Andean pasture at sunrise. The animal occupies the left third of the widescreen frame while layered golden puna grass, low stone walls, and blue volcanic ridges create strong depth behind it. Beginning from the opening pose, a light mountain breeze ripples its long silky fleece and bends the foreground grass; the alpaca lifts its chin, turns calmly toward the lens, blinks, and takes one measured step forward. The camera makes a slow low-angle dolly to the right, producing gentle parallax between grass, animal, stone wall, and distant peaks. Warm amber rim light outlines the fleece against cool mineral-blue mountains, with restrained natural-history editorial color and realistic hoof contact, anatomy, shadows, and wind physics. Premium agricultural documentary cinematography, serene and credible rather than sentimental. Synchronized sound of soft wind through dry grass, one quiet alpaca breath, faint distant pasture birds, and subtle hoof movement on firm soil. No people, fences crossing the animal, buildings, captions, logos, or music.",
  "resolution": "720p",
  "duration": 5,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/92f275cd-34ce-467d-9d79-cb86e10236c0.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

### first-last-frame (first-last-frame)

[Watch video](https://assets.runware.ai/examples/bytedance-seedance-2-0-fast/d3182c5b-fa1a-4960-ab29-12fd210406e3.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "1e4a5336-d9b3-423b-a56c-fe8f26d745f1",
  "model": "bytedance:seedance@2.0-fast",
  "positivePrompt": "Create an eight-second locked-camera background-replacement reveal for a wheelchair-fencing championship campaign. Begin exactly from the supplied first frame: the female athlete, foil, clothing, mask, straps, wheels, and cobalt hubs must remain sharply consistent in identity, proportions, position, and three-quarter pose. She stays nearly still with only natural breathing, a tiny settling motion in the glove, and a subtle metallic vibration at the foil tip. Over the transition, a narrow cobalt light sweep travels from screen left to right across the gray cyclorama. Directly behind that sweep, the plain studio transforms through a clean, physically plausible match dissolve into the supplied championship arena: metallic piste markings extend across the floor, realistic reflections develop beneath the wheels, tiered seating resolves through restrained haze, and warm amber rim lights switch on sequentially in depth. Preserve perfect subject edges and natural contact shadows throughout; do not dissolve, duplicate, deform, or restyle the athlete or wheelchair. End exactly on the supplied last frame and hold briefly with the completed arena fully stable. Synchronized stereo sound: begin with quiet studio ventilation and a faint fluorescent hum; match the moving light sweep with a soft electrical whoosh traveling left to right; add crisp floor-panel clicks as the piste forms, then let distant arena ambience and a restrained crowd swell fade in naturally. Finish with one clean metallic foil ring and a short reverberant arena tail. No speech, music, logos, captions, or on-screen text.",
  "resolution": "480p",
  "duration": 8,
  "settings": {
    "audio": true
  },
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/a88c187e-86a7-44eb-aaef-b75693bc22ab.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/d12bc741-0362-47d6-90c6-0c3968fa4987.jpg",
        "frame": "last"
      }
    ]
  }
}
```

---

### reference-to-video (reference-to-video)

[Watch video](https://assets.runware.ai/examples/bytedance-seedance-2-0-fast/078231dd-488b-45ba-83c0-2b01cd54edb6.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "a57c3c46-2ab4-404e-85e6-cb6b30190dc2",
  "model": "bytedance:seedance@2.0-fast",
  "positivePrompt": "Create a finished 10-second portrait cinematic title sequence for a premium factual docuseries about forensic document examiners tracing counterfeit currency. The final series title is “FALSE IMPRESSIONS.” Use all three references as coordinated guidance. The reference image defines the authentic copper patina, turquoise oxidation, engraved crosshatching and recurring guilloché line vocabulary; preserve those material qualities and ornamental motifs without reproducing any readable currency text, denomination, government emblem or real banknote. The reference video defines the grounded movement of the intaglio press, the macro camera language, gloved handling and the cadence of the cuts. The reference audio is the master timing guide: synchronize cuts and physical actions to its press clacks, bass pulse, prepared-piano accents and final heavy impact.\n\nVertical 9:16 composition with strong central framing and generous title-safe space. Premium forensic-thriller mood rather than a commercial. Art direction: tactile copper, oxidized cyan, bone-white paper and dense carbon black; crisp raking light, shallow macro focus, subtle suspended paper dust, restrained film grain, realistic printing physics.\n\nShot progression: 0.0–2.2 seconds, begin inside an extreme macro labyrinth of engraved guilloché grooves from the reference plate. A narrow blade of cyan light travels across the copper while the camera glides forward as though following evidence through a maze. Fine ink gathers naturally in recessed lines. Cut exactly on the first strong press clack. 2.2–4.5 seconds, lateral macro tracking inspired by the reference video as the plate passes beneath the steel roller. Paper compresses under convincing pressure; engraved lines transfer from copper to fiber in perfect registration. Each mechanical contact lands on an audio accent. 4.5–6.8 seconds, a white cotton-gloved forensic examiner lifts the damp sheet toward a cold inspection lamp. Rack focus through layered security lines, tiny paper fibers and a partial engraved eye; a brief oblique shimmer reveals one broken line that suggests a counterfeit flaw. Do not show the examiner’s face. 6.8–8.3 seconds, rapid but elegant evidence montage timed to the rising metallic tension: loupe glass crossing ink ridges, a needle marking a microscopic discontinuity, black powder catching on embossed paper, guilloché curves aligning into letter-like geometry. Keep every insert photorealistic and materially consistent with the references. 8.3–10.0 seconds, on the final heavy roller impact, the engraved geometry snaps into a clean centered title card reading “FALSE IMPRESSIONS” in uppercase copperplate-inspired lettering, apparently pressed into bone-white rag paper with subtle black ink ridges and cyan oxidation at the edges. Hold long enough to read while the final resonance decays. No subtitle, credits, logos, dates, denominations or other visible words. Generate synchronized stereo audio led by the supplied music reference, retaining its rhythm and adding only natural close press mechanics, paper friction and room tone.",
  "width": 720,
  "height": 1280,
  "duration": 10,
  "settings": {
    "audio": true
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/3679a06b-168f-431a-b52b-b28ba325f27d.jpg"
    ],
    "referenceVideos": [
      "https://assets.runware.ai/assets/inputs/c3b4bf34-8035-4fd2-8a65-ec604d1718ef.mp4"
    ],
    "referenceAudios": [
      "https://assets.runware.ai/assets/inputs/910f64c1-4614-4362-a162-5bafdb4db85c.mp3"
    ]
  }
}
```