---
title: Seedance 2.5 Flash | Runware Docs
url: https://runware.ai/docs/models/bytedance-seedance-2-5-flash
description: Lower-cost Seedance 2.5 video generation with 30-second clips, multimodal references, and video editing
---
# Seedance 2.5 Flash

![Seedance 2.5 Flash](https://assets.runware.ai/covers/bytedance-seedance-2-5-flash.jpg)

Seedance 2.5 Flash is a lighter, lower-cost variant of ByteDance's Seedance 2.5 video model. It keeps the same multimodal workflow, generating from a prompt, first and last frames, or up to 10 reference images, 5 reference videos and 5 reference audio clips, and it edits or extends an existing clip, producing 4 to 30 second videos with synchronized audio at 480p or 720p. It suits high-volume iteration, previews, and social content where the higher Seedance 2.5 resolutions are not needed.

- **Status**: live
- **ID**: `bytedance:seedance@2.5-flash`
- Try in Playground
- **Creator**: ByteDance
- **Release Date**: November 15, 2026
- **Capabilities**: Text to Video, Image to Video, Video to Video, Audio to Video, Edit, Extend, Checkpoint, Audio

## Pricing

$0.0678 from, per second · ~1m 20s per request

**Rates** (per second)

- Text/Image to Video · 480p: `$0.0678`
- Text/Image to Video · 720p: `$0.152`
- Video-to-Video · 480p: `$0.0833`
- Video-to-Video · 720p: `$0.187`

**6 example generations**

- [first-last-frame](https://runware.ai/docs/models/bytedance-seedance-2-5-flash/examples#example-alpine-seed-bank-seasonal-visualization) · 480p · 7s: `$0.474` (~1m 14s)
- [text-to-video](https://runware.ai/docs/models/bytedance-seedance-2-5-flash/examples#example-automatic-flood-barrier-product-demo) · 720p · 5s · audio: `$0.762` (~1m 19s)
- [first-frame](https://runware.ai/docs/models/bytedance-seedance-2-5-flash/examples#example-seed-vault-film-stock-transition) · 720p · 6s: `$0.913` (~1m 23s)
- [video-edit](https://runware.ai/docs/models/bytedance-seedance-2-5-flash/examples#example-predawn-vineyard-frost-patrol) · 720p · autos: `$1.09` (~1m 22s)
- [video-extend](https://runware.ai/docs/models/bytedance-seedance-2-5-flash/examples#example-archival-textile-conservation-b-roll) · 720p · 6s: `$1.11` (~1m 16s)
- [reference-to-video](https://runware.ai/docs/models/bytedance-seedance-2-5-flash/examples#example-groundwater-documentary-teaser-sequence) · 720p · 8s: `$1.30` (~1m 48s)

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

## Compatibility & Validation

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

---

When `inputs.frameImages` or `inputs.video` is provided, `width/height` cannot be used.

---

When none of `inputs.frameImages`, `inputs.referenceImages`, `inputs.referenceVideos`, `inputs.referenceAudios`, or `inputs.video` are provided, `positivePrompt` is required.

---

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

---

When `settings.operation` is provided, `inputs.video` is required.

---

When `settings.operation` is `edit`, `duration` must be `auto`.

---

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

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `480p (~16:9)` | `854x480` |
| `480p (~4:3)` | `752x560` |
| `480p (1:1)` | `640x640` |
| `480p (~3:4)` | `560x752` |
| `480p (~9:16)` | `480x854` |
| `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` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#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-2-5-flash#request-outputtype)

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

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#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-2-5-flash#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-2-5-flash#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-2-5-flash#request-deliverymethod)

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

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

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

### [uploadEndpoint](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#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-2-5-flash#request-safety)

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

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#request-safety-checkcontent)

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

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

#### [mode](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#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-2-5-flash#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-2-5-flash#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#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-2-5-flash#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `10`
- **File size (each)**: `up to 30 MB`
- **Size (each)**: `300 px to 6000 px`
- **Aspect ratio (each)**: `1:2.5 to 2.5:1`

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

### [frameImages](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `1`
- **Max items**: `2`
- **Size (each)**: `300 px to 6000 px`
- **Aspect ratio (each)**: `1:2.5 to 2.5:1`

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-2-5-flash#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-2-5-flash#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).

### [video](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#request-inputs-video)

- **Path**: `inputs.video`
- **Type**: `string`
- **File size**: `up to 200 MB`
- **Duration**: `2s to 30s`
- **Size**: `300 px to 6000 px`
- **Aspect ratio**: `1:2.5 to 2.5:1`

Video input (UUID or URL). The source clip to edit or extend.

### [referenceVideos](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#request-inputs-referencevideos)

- **Path**: `inputs.referenceVideos`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `5`
- **File size (each)**: `up to 200 MB`
- **Duration (each)**: `2s to 30s`
- **Duration (total)**: `up to 30s`
- **Size (each)**: `300 px to 6000 px`
- **Aspect ratio (each)**: `1:2.5 to 2.5:1`

List of reference videos (UUID or URL). Used as visual guidance for a new video. To edit or extend an existing clip, use `inputs.video` instead.

### [referenceAudios](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#request-inputs-referenceaudios)

- **Path**: `inputs.referenceAudios`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `5`
- **File size (each)**: `up to 15 MB`
- **Duration (each)**: `2s to 30s`
- **Duration (total)**: `up to 30s`

List of reference audios (UUID or URL).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `bytedance:seedance@2.5-flash`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**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-2-5-flash#request-positiveprompt)

- **Type**: `string`
- **Required**: conditional — Required when inputs.frameImages and inputs.referenceImages and inputs.referenceVideos and inputs.referenceAudios and inputs.video are not provided
- **Min**: `2`
- **Max**: `50000`

Text prompt describing elements to include in the generated output. Reference assets in array order as `@Image1`, `@Video1`, and `@Audio1`, numbered from one.

**Learn more** (1 resource):

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

### [width](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#request-width)

- **Type**: `integer`
- **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-2-5-flash#request-height)

- **Type**: `integer`
- **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-2-5-flash#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-2-5-flash#request-duration)

- **Type**: `integer | string`
- **Min**: `4`
- **Max**: `30`
- **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).

**Allowed values**: `auto`

### [seed](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `2147483647`

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

**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-2-5-flash#request-settings-audio)

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

Generate synchronized audio.

### [operation](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#request-settings-operation)

- **Path**: `settings.operation`
- **Type**: `string`

Operation to perform on the source video. When omitted, the prompt decides which one runs.

**Allowed values**:

- `edit` Modify the source clip.
- `extend` Continue the source clip beyond its original ending.

## Response Parameters

### [taskType](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#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-2-5-flash#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-2-5-flash#response-videouuid)

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

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#response-videourl)

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

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#response-videodatauri)

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

Data URI of the output video.

### [seed](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#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-2-5-flash#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/bytedance-seedance-2-5-flash#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-2-5-flash/c917e839-1d17-4019-9677-d9276f1e55da.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "867a2e67-254f-4be6-87de-0c92e68b1782",
  "model": "bytedance:seedance@2.5-flash",
  "positivePrompt": "Create a polished industrial product demonstration in one continuous portrait shot. Show a full-scale cutaway of a modern shop doorway inside a dark, controlled test facility. The doorway threshold contains a slim stainless-steel automatic flood barrier, clearly visible in the lower center of the vertical frame. Begin with the barrier flush to the floor and stacked cardboard parcels safely visible on the dry side. A powerful surge of blue-tinted test water rushes toward the entrance from the foreground. As water reaches the threshold, the buoyant silver barrier rises smoothly from its recessed housing, locks upright, and redirects the churning water sideways while the floor and parcels behind it remain completely dry. Finish with water pressing against the raised barrier and droplets sparkling in cool laboratory light. Use precise photorealistic engineering detail, dramatic cyan water against warm amber practical lights, crisp reflections, subtle slow-motion emphasis at deployment, and a gentle forward camera push that keeps the full mechanism and dry protected side legible. No people, labels, logos, captions, diagrams, interface graphics, or floating text. Synchronized audio: a low mechanical room hum, rapidly approaching water, a forceful splash, smooth metallic lift and locking click, then sustained water turbulence on the wet side with quiet dry-room ambience behind the barrier.",
  "width": 720,
  "height": 1280,
  "duration": 5,
  "settings": {
    "audio": true
  }
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/bytedance-seedance-2-5-flash/a5a688da-a957-4f5f-9ba8-9cf742b2c0ac.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "908ddc53-1ac3-4f81-8f4b-1c46c297b931",
  "model": "bytedance:seedance@2.5-flash",
  "positivePrompt": "Begin exactly from @Image1 and continue it as one uninterrupted documentary shot. Preserve the seed vault, shelving, curator, wardrobe, geometry, and symmetrical framing. The camera makes a very slow, steady push down the central aisle while the curator turns the metal wheel and the mobile shelving begins to open with heavy mechanical motion. Her breath drifts naturally in the freezing air and a light veil of frost dust falls from the shelf edges. As the aisle opens, transition the photographic atmosphere gradually from the clean, cool modern digital look of the first frame into authentic late-1970s 16mm reversal-film character: tactile fine grain that grows organically, gently lifted blacks, cyan-green shadows, restrained amber highlights, mild halation around fluorescent tubes, subtle exposure breathing, slight gate weave, softened micro-contrast, and modest period color fading. Make the film-stock transition continuous and motivated by the advancing camera and flickering overhead lights, not an abrupt filter switch. End fully immersed in the archival film look while retaining realistic skin, fabric, metal, frost, and seed-box detail. Natural synchronized sound only: low refrigeration hum, distant ventilation, the groan and clatter of moving steel shelves, glove against the wheel, soft footsteps, and quiet breathing; no music, narration, or speech.",
  "resolution": "720p",
  "duration": 6,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/a3c89424-63dd-40c2-86ab-79d9c1ca9478.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/bytedance-seedance-2-5-flash/af4a1a9b-d2cb-41ba-80b6-2fa8b03e99a3.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "ace96e52-f263-4ed5-8b95-df87e81cabe1",
  "model": "bytedance:seedance@2.5-flash",
  "positivePrompt": "Create one continuous cinematic seasonal time-lapse that begins exactly on @Image1 and ends exactly on @Image2. Keep the camera completely locked and preserve the seed bank's architecture, entrance geometry, path, marker poles, mountain silhouette, perspective, and composition without warping or object drift. Over the take, windblown winter spindrift streams naturally across the ground, storm clouds race overhead, and the indigo blue-hour light gradually warms. The snowpack settles and recedes in a smooth accelerated thaw, ice becoming small reflective rivulets along the path while muted moss and dwarf alpine grasses are revealed beneath it. The clouds thin and part as soft late-spring dawn sunlight reaches the valley, arriving precisely at the final frame. Maintain restrained premium architectural-film realism, subtle filmic contrast, slate blue, rust, concrete gray, moss green, and pale gold. No cut, dissolve, camera movement, people, vehicles, text, logos, or changes to the building. Synchronized natural sound evolves from forceful winter wind and granular snow hiss into gentler air, trickling meltwater, and a few distant alpine birds; no music or speech.",
  "resolution": "480p",
  "duration": 7
}
```

---

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

[Watch video](https://assets.runware.ai/examples/bytedance-seedance-2-5-flash/4b946af0-8aba-41b3-b7fe-72a2f349bdab.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "eb785595-b08c-4270-bc91-d09bd7dc6b73",
  "model": "bytedance:seedance@2.5-flash",
  "positivePrompt": "Create an 8-second 16:9 cinematic teaser and title sequence for a prestige investigative documentary about disappearing groundwater titled “THE HIDDEN RIVER.” Use @Image1 as the visual design reference for the hydrogeological drafting-table world, mineral-blue and oxidized-copper palette, archival paper texture, contour-line detail and directional lighting. Use @Video1 specifically as the motion reference: slow controlled macro push-in, shallow depth of field and branching capillary movement. Use @Audio1 as the soundtrack and sound-design guide, synchronizing the subterranean drone, restrained metal ticks and final low impact to the visual beats.\n\n0.0–2.0 seconds: begin almost black on an extreme macro view of dry archival paper. A thin luminous blue seep enters from the lower edge and travels through the fibers like groundwater, revealing fragments of hand-drawn aquifer contours beneath the surface. One distant metallic tick lands as a contour line catches the light.\n\n2.0–5.2 seconds: continue the slow push forward as the blue veins branch into a vast underground watershed diagram. Fine desert dust lifts in miniature waves, suggesting a landscape seen from high altitude, while rusted survey marks and hairline copper geometry emerge from darkness. Keep the imagery tactile, practical and photorealistic rather than holographic; elegant optical transitions, subtle film grain, deep blacks, no people.\n\n5.2–8.0 seconds: the branching water lines converge into negative space at center. On the low impact, reveal the exact title “THE HIDDEN RIVER” in large, sharply legible uppercase condensed serif lettering, pale limestone white with a faint blind-embossed paper texture. Hold the centered title long enough to read while the blue seep continues moving almost imperceptibly underneath. Finish on a clean, composed title card with no subtitle, credits, logos, extra words, borders or interface elements. Premium natural-history and investigative-documentary tone: ominous, precise, restrained and cinematic.",
  "resolution": "720p",
  "duration": 8,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/9986413d-6e50-494c-9f36-483de6d2a2f0.jpg"
    ],
    "referenceVideos": [
      "https://assets.runware.ai/assets/inputs/064b1e8f-5149-441e-9afb-2a23320db4ca.mp4"
    ],
    "referenceAudios": [
      "https://assets.runware.ai/assets/inputs/2c26d2d2-7dee-4728-9ca8-89bda5acfbd3.mp3"
    ]
  }
}
```

---

### video-edit (video-edit)

[Watch video](https://assets.runware.ai/examples/bytedance-seedance-2-5-flash/811162bf-0d5d-40f1-b822-a5a24fcbde92.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "54ea738c-765e-4866-b509-44942caf8812",
  "model": "bytedance:seedance@2.5-flash",
  "positivePrompt": "Edit @Video1 into a seamless, photorealistic day-for-night agricultural documentary shot set around 4:30 a.m. during a vineyard frost patrol. Preserve the source clip’s exact vineyard manager, clothing, handheld temperature probe, walking action, tractor, grape-row layout, camera path, framing, timing and natural body motion. Relight the entire scene consistently: deep cobalt predawn sky, cool moonlit highlights, subdued exposure, soft silver edge light on the worker and vines, realistic dark shadows with retained detail, and a thin sparkle of frost on leaves and ground. Add restrained warm practical illumination from the tractor work lamps in the background, with physically accurate light falloff and no artificial neon look. Remove all visual cues of midday sun, including bright blue daylight, hard overhead illumination and warm daytime color. Maintain stable identities, object geometry, textures, reflections, occlusion and temporal coherence in every frame. Keep the result natural and observational rather than stylized or theatrical. Adapt the synchronized location audio to the new time of day: quiet diesel idle, soft footsteps on frosty soil, a distant wind machine, light cold wind and sparse nocturnal insects; remove prominent daytime birds while preserving action synchronization. No text, captions, logos, cuts, speed changes or new people.",
  "resolution": "720p",
  "duration": "auto",
  "settings": {
    "operation": "edit"
  },
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/dae9a3cf-fe12-404f-b97c-4de8c3415fd9.mp4"
  }
}
```

---

### video-extend (video-extend)

[Watch video](https://assets.runware.ai/examples/bytedance-seedance-2-5-flash/f525036d-6b36-435e-9395-ba5fbc9ebc2c.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "d7ec9b3e-f6d2-4c95-87a6-304bc67d4aad",
  "model": "bytedance:seedance@2.5-flash",
  "positivePrompt": "Extend @Video1 naturally beyond its final frame as one uninterrupted documentary b-roll shot. Preserve the same conservator, blue nitrile gloves, antique botanical embroidery, archival worktable, conservation brush, vacuum nozzle, soft north-window lighting, muted sage and dusty-rose palette, shallow practical depth of field, and restrained museum-documentary realism. Continue the existing slow left-to-right tabletop slider trajectory at exactly the same pace with no cut, reframing, zoom, or speed change. The brush makes gentle contact with the dusty embroidered fern and completes two careful, controlled strokes toward the low-suction nozzle. A few tiny dust fibers lift and disappear into the nozzle without dramatic particles. The conservator then pauses, rotates the brush slightly between gloved fingers, and begins a third delicate stroke as the camera continues gliding right. Maintain accurate hand anatomy, stable textile patterns, realistic fabric response, and subtle professional movements. Continue the existing synchronized location sound seamlessly: quiet room tone, faint ventilation, soft bristle contact, minimal fabric rustle, and a barely audible vacuum hum. No speech, music, text, logos, new people, or added objects. Do not modify the source footage; only continue what happens after it ends.",
  "resolution": "720p",
  "duration": 6,
  "settings": {
    "operation": "extend"
  },
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/0c47c0d7-2f0b-4bf7-bfd3-b8b75e58a483.mp4"
  }
}
```