---
title: FLUX Video Edit [fast] | Runware Docs
url: https://runware.ai/docs/models/bfl-flux-video-edit-fast
description: Fast prompt-driven video editing that preserves the source clip's motion, timing, framing, and audio
---
# FLUX Video Edit [fast]

![FLUX Video Edit [fast]](https://assets.runware.ai/covers/bfl-flux-video-edit-fast.jpg)

FLUX Video Edit [fast] is Black Forest Labs' instruction-based video editing model for changing an existing clip with a natural-language prompt. It can add, remove, or replace objects and characters; alter settings, styles, actions, and on-screen text; and revise or translate dialogue while preserving unedited motion, camera work, timing, framing, and audio. It supports source clips up to 15 seconds and produces 24 FPS output at up to 720p while retaining the original duration and aspect ratio.

- **Status**: live
- **ID**: `bfl:flux@video-edit-fast`
- Try in Playground
- **Creator**: Black Forest Labs
- **Release Date**: September 9, 2026
- **Capabilities**: Video to Video, Edit, Checkpoint

## Pricing

$0.03 per second · ~51s per request

**4 example generations**

- [video-edit](https://runware.ai/docs/models/bfl-flux-video-edit-fast/examples#example-municipal-water-documentary-title-sequence): `$0.181` (~54s)
- [video-edit](https://runware.ai/docs/models/bfl-flux-video-edit-fast/examples#example-widescreen-ceramic-workshop-outpaint): `$0.181` (~45s)
- [video-edit](https://runware.ai/docs/models/bfl-flux-video-edit-fast/examples#example-lighthouse-archive-film-restoration): `$0.181` (~2m 58s)
- [video-edit](https://runware.ai/docs/models/bfl-flux-video-edit-fast/examples#example-falconry-exhibition-miniature-reel): `$0.181` (~48s)

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

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/bfl-flux-video-edit-fast#request-tasktype)

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

Identifier for the type of task being performed

### [taskUUID](https://runware.ai/docs/models/bfl-flux-video-edit-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/bfl-flux-video-edit-fast#request-outputtype)

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

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/bfl-flux-video-edit-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/bfl-flux-video-edit-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/bfl-flux-video-edit-fast#request-webhookurl)

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

Specifies a webhook URL where JSON responses will be sent 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/platform/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/bfl-flux-video-edit-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/platform/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/bfl-flux-video-edit-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/bfl-flux-video-edit-fast#request-safety)

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

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/bfl-flux-video-edit-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/bfl-flux-video-edit-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/bfl-flux-video-edit-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/bfl-flux-video-edit-fast#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/bfl-flux-video-edit-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.

### [video](https://runware.ai/docs/models/bfl-flux-video-edit-fast#request-inputs-video)

- **Path**: `inputs.video`
- **Type**: `string`
- **Required**: true
- **File size**: `up to 50 MB`
- **Duration**: `0.7s to 15s`
- **Size**: `160 px or more`

Video input (UUID or URL). The output keeps the source duration, aspect ratio and audio, at 24 fps. A source above 720p is downscaled to 720p.

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/bfl-flux-video-edit-fast#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `bfl:flux@video-edit-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/bfl-flux-video-edit-fast#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `4096`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

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

**Settings**

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

### [safetyTolerance](https://runware.ai/docs/models/bfl-flux-video-edit-fast#request-settings-safetytolerance)

- **Path**: `settings.safetyTolerance`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `4`
- **Default**: `2`

Tolerance level for content moderation. Lower values are stricter; higher values are more permissive.

## Response Parameters

### [taskType](https://runware.ai/docs/models/bfl-flux-video-edit-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/bfl-flux-video-edit-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/bfl-flux-video-edit-fast#response-videouuid)

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

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/bfl-flux-video-edit-fast#response-videourl)

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

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/bfl-flux-video-edit-fast#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/bfl-flux-video-edit-fast#response-videodatauri)

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

Data URI of the output video.

### [seed](https://runware.ai/docs/models/bfl-flux-video-edit-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/bfl-flux-video-edit-fast#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/bfl-flux-video-edit-fast#response-cost)

- **Type**: `float`

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

## Examples

### video-edit (video-edit)

[Watch video](https://assets.runware.ai/examples/bfl-flux-video-edit-fast/23cacbae-648a-481b-a7e8-f5c32d037c63.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "564ee432-ea2d-416b-9e9c-3d6fb48b030a",
  "model": "bfl:flux@video-edit-fast",
  "positivePrompt": "Transform this source clip into a tense prestige-documentary title sequence about the vast water infrastructure hidden beneath a city. Preserve the original continuous camera move, the engineer's identity, walking pace, body motion, rotating machinery, framing, timing and natural audio. Replace the daylight treatment plant with a monumental subterranean brutalist reservoir at night: immense wet concrete vaults disappearing into darkness, oxidized steel catwalks, black water below and distant tunnels. Keep the engineer walking naturally on the same catwalk, now illuminated by intermittent amber maintenance lamps and cold cyan reflections rising from the water. Add subtle volumetric mist, dripping condensation, ripples and realistic reflections that remain spatially and temporally consistent as the camera moves. Introduce restrained cyanotype-style engineering diagrams and pipe-network contour lines as faint translucent projections traveling across the concrete walls, physically anchored to their surfaces rather than appearing as interface graphics. Build visual tension gradually: begin nearly black and industrial, reveal more of the cavern with passing lights, then let the cyan reflections intensify during the final three seconds. At the end, form the documentary title BENEATH THE CITY in large condensed uppercase lettering from pale mineral deposits on the far concrete wall. The title must be correctly spelled, centered, legible and integrated into the environment with damp texture and grazing light. Add a smaller line beneath reading A DOCUMENTARY SERIES. No other text, logos, subtitles, borders or interface elements. Photorealistic cinematic finish, deep blacks, silver concrete, oxidized orange and electric cyan palette, subtle 35mm grain, controlled highlights and ominous institutional atmosphere.",
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/7750d507-78ff-43a2-acd8-e517b566e5b9.mp4"
  }
}
```

---

### video-edit (video-edit)

[Watch video](https://assets.runware.ai/examples/bfl-flux-video-edit-fast/1d78dc94-cd06-451a-8672-c206beecc307.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "bd8508b5-5f84-4702-80d6-eac498f44340",
  "model": "bfl:flux@video-edit-fast",
  "positivePrompt": "Outpaint the centered portrait footage across the full widescreen frame, completely replacing both dark side mattes with a natural continuation of the same working ceramics studio. Preserve the original central action, timing, camera position, artisan, cobalt-blue vessel, kiln, smoke movement, flickering light, and audio. Extend the kiln and soot-darkened brick wall toward frame left; add orderly shelves of unglazed clay vessels, hanging iron tools, a scarred timber workbench, and stacked firebricks toward frame right. Continue all smoke, shadows, firelight, and subtle reflections coherently into the newly created areas throughout the shot. Match the central footage's perspective, lens softness, exposure, grain, terracotta-and-cobalt palette, and tactile editorial documentary style. The expansion must feel like one authentic continuous camera capture with no seams, borders, duplicated objects, abrupt changes, text, logos, or added camera movement.",
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/ceba33dc-a639-4307-957b-0fc00eb9a90c.mp4"
  }
}
```

---

### video-edit (video-edit)

[Watch video](https://assets.runware.ai/examples/bfl-flux-video-edit-fast/13c24539-f37e-4f4f-9fc2-6511cce11376.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "6e034771-32e6-4062-83fc-646f46fb43e8",
  "model": "bfl:flux@video-edit-fast",
  "positivePrompt": "Restore this damaged archival lighthouse footage for a maritime museum exhibition. Remove dust, hairs, vertical scratches, chemical blotches, torn-edge artifacts, frame jitter, gate weave, and harsh exposure flicker. Repair brief emulsion-damaged areas with temporally consistent detail so the keeper, hand crank, rotating Fresnel lens, windows, and ocean remain stable from frame to frame. Recover natural contrast and shadow detail without making the image look digitally sharpened. Apply restrained, historically plausible colorization: weathered warm brass on the lens mechanism, clear glass prisms with subtle spectral highlights, off-white painted ironwork, muted navy wool uniform, brown leather belt and boots, pale cool daylight, and a desaturated blue-gray sea. Preserve the keeper's exact hand-cranking action, the lens rotation, ocean movement, original camera position, framing, timing, and audio. Retain fine authentic 16mm grain and a gently aged texture, but deliver a clean, coherent, museum-grade restoration with no modern objects, invented text, or color pulsing.",
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/77ef9537-4222-4bbf-8a9a-a3d7b2945b10.mp4"
  }
}
```

---

### video-edit (video-edit)

[Watch video](https://assets.runware.ai/examples/bfl-flux-video-edit-fast/88c76cc4-f2c1-491a-90d8-a8e3298301c1.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "73720225-4e97-47d7-8d18-018d60d990c5",
  "model": "bfl:flux@video-edit-fast",
  "positivePrompt": "Restyle the entire live-action clip as a richly animated Persian illuminated manuscript miniature created with opaque mineral pigments and gold leaf on warm ivory paper. Preserve the original camera movement, framing, timing, falconer's identity and body motion, and the hawk's exact launch path, wingbeats, anatomy and flight speed. Render the falconer with elegant flattened shapes, precise ink contours and finely patterned garments in lapis blue, vermilion, turquoise and muted saffron. Transform the grassland into a decorative manuscript landscape of rhythmic gold grasses, small stylized flowers, patterned earth and distant cobalt hills. Give the hawk especially crisp feather detailing and a readable silhouette in every frame. Add subtle handmade paper grain, delicate brush variation and restrained gold shimmer that remains temporally stable. Keep all elements coherent from frame to frame with no flicker, morphing, duplicated limbs, extra birds or added lettering. The finished result should feel like a historical miniature brought gracefully to life for a prestigious museum exhibition campaign, while retaining the source audio unchanged.",
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/bacbd6ab-b55b-42d1-8962-3fa315075725.mp4"
  }
}
```