Xai Grok Imagine Video API

Image To Video
Text To Video
Reference To Video
Edit Video
Extend Video

Endpoint: POST https://fal.run/xai/grok-imagine-video/image-to-video Endpoint ID: xai/grok-imagine-video/image-to-video

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "xai/grok-imagine-video/image-to-video",
    arguments={
        "prompt": "Medieval knight in ornate armor walking through a mystical forest, bioluminescent plants pulsing with light, ancient stone ruins overgrown with glowing vines, over-the-shoulder camera, dark fantasy aesthetic, volumetric fog and Lumen lighting",
        "image_url": "https://v3b.fal.media/files/b/0a8b90e0/BFLE9VDlZqsryU-UA3BoD_image_004.png"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Input Schema

prompt

string

required

Text description of desired changes or motion in the video.

duration

integer

default:"6"

Video duration in seconds. Default value: 6Range: 1 to 15

aspect_ratio

Enum

default:"auto"

Aspect ratio of the generated video. Default value: autoPossible values: auto, 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16

resolution

ResolutionEnum

default:"720p"

Resolution of the output video. Default value: "720p"Possible values: 480p, 720p

image_url

string

required

URL of the input image for video generation.

Output Schema

video

VideoFile

required

The generated video.

Input Example

{
  "prompt": "Medieval knight in ornate armor walking through a mystical forest, bioluminescent plants pulsing with light, ancient stone ruins overgrown with glowing vines, over-the-shoulder camera, dark fantasy aesthetic, volumetric fog and Lumen lighting",
  "duration": 6,
  "aspect_ratio": "auto",
  "resolution": "720p",
  "image_url": "https://v3b.fal.media/files/b/0a8b90e0/BFLE9VDlZqsryU-UA3BoD_image_004.png"
}

Output Example

{
  "video": {
    "content_type": "video/mp4",
    "duration": 6.041667,
    "file_name": "0Ci1dviuSnEyUZzBUq-_5_nu7MrAAa.mp4",
    "fps": 24,
    "height": 720,
    "num_frames": 145,
    "url": "https://v3b.fal.media/files/b/0a8b90e0/0Ci1dviuSnEyUZzBUq-_5_nu7MrAAa.mp4",
    "width": 1280
  }
}

Endpoint: POST https://fal.run/xai/grok-imagine-video/text-to-video Endpoint ID: xai/grok-imagine-video/text-to-video

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "xai/grok-imagine-video/text-to-video",
    arguments={
        "prompt": "Anime schoolgirl bursting out of house door, cherry blossoms blowing, morning light, speed lines indicating rush, chibi-ready expressions, classic shojo aesthetic, vibrant colors"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Input Schema

prompt

string

required

Text description of the desired video.

duration

integer

default:"6"

Video duration in seconds. Default value: 6Range: 1 to 15

aspect_ratio

AspectRatioEnum

default:"16:9"

Aspect ratio of the generated video. Default value: "16:9"Possible values: 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16

resolution

ResolutionEnum

default:"720p"

Resolution of the output video. Default value: "720p"Possible values: 480p, 720p

Output Schema

video

VideoFile

required

The generated video.

Input Example

{
  "prompt": "Anime schoolgirl bursting out of house door, cherry blossoms blowing, morning light, speed lines indicating rush, chibi-ready expressions, classic shojo aesthetic, vibrant colors",
  "duration": 6,
  "aspect_ratio": "16:9",
  "resolution": "720p"
}

Output Example

{
  "video": {
    "content_type": "video/mp4",
    "duration": 6.041667,
    "file_name": "RUAbFYlssdqnbjNLmE8qP_IX7BNYGP.mp4",
    "fps": 24,
    "height": 720,
    "num_frames": 145,
    "url": "https://v3b.fal.media/files/b/0a8b90e4/RUAbFYlssdqnbjNLmE8qP_IX7BNYGP.mp4",
    "width": 1280
  }
}

Endpoint: POST https://fal.run/xai/grok-imagine-video/reference-to-video Endpoint ID: xai/grok-imagine-video/reference-to-video

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "xai/grok-imagine-video/reference-to-video",
    arguments={
        "prompt": "A @Image1 running through a sunlit meadow, cinematic slow motion",
        "reference_image_urls": [
            "https://v3b.fal.media/files/b/0a8b90e0/BFLE9VDlZqsryU-UA3BoD_image_004.png"
        ]
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Examples

This man walking in this road between columns

Input Schema

prompt

string

required

Text prompt describing the video to generate. Use @Image1, @Image2, etc. to reference specific images from reference_image_urls in order.

reference_image_urls

list<string>

required

One or more reference image URLs to guide the video generation as style and content references. Reference in prompt as @Image1, @Image2, etc. Maximum 7 images.

duration

integer

default:"8"

Video duration in seconds. Default value: 8Range: 1 to 10

aspect_ratio

AspectRatioEnum

default:"16:9"

Aspect ratio of the generated video. Default value: "16:9"Possible values: 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16

resolution

ResolutionEnum

default:"480p"

Resolution of the output video. Default value: "480p"Possible values: 480p, 720p

Output Schema

video

VideoFile

required

The generated video.

Input Example

{
  "prompt": "A @Image1 running through a sunlit meadow, cinematic slow motion",
  "reference_image_urls": [
    "https://v3b.fal.media/files/b/0a8b90e0/BFLE9VDlZqsryU-UA3BoD_image_004.png"
  ],
  "duration": 8,
  "aspect_ratio": "16:9",
  "resolution": "480p"
}

Output Example

{
  "video": {
    "content_type": "video/mp4",
    "duration": 8,
    "file_name": "r2v_output.mp4",
    "fps": 24,
    "height": 720,
    "num_frames": 192,
    "url": "https://v3b.fal.media/files/b/0a8b90e4/r2v_output.mp4",
    "width": 1280
  }
}

Endpoint: POST https://fal.run/xai/grok-imagine-video/edit-video Endpoint ID: xai/grok-imagine-video/edit-video

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "xai/grok-imagine-video/edit-video",
    arguments={
        "prompt": "Colorize the video",
        "video_url": "https://v3b.fal.media/files/b/0a8b9112/V5Z_NIPE3ppMDWivNo6_q_video_019.mp4"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Input Schema

prompt

string

required

Text description of the desired edit.

video_url

string

required

URL of the input video to edit. The video will be resized to a maximum area of 854x480 pixels and truncated to 8 seconds.

resolution

ResolutionEnum

default:"auto"

Resolution of the output video. Default value: "auto"Possible values: auto, 480p, 720p

Output Schema

video

VideoFile

required

The generated video.

Input Example

{
  "prompt": "Colorize the video",
  "video_url": "https://v3b.fal.media/files/b/0a8b9112/V5Z_NIPE3ppMDWivNo6_q_video_019.mp4",
  "resolution": "auto"
}

Output Example

{
  "video": {
    "content_type": "video/mp4",
    "duration": 5.041667,
    "file_name": "EuDrZuQTW9m1phBXOsauz_EpJH3s8X.mp4",
    "fps": 24,
    "height": 720,
    "num_frames": 121,
    "url": "https://v3b.fal.media/files/b/0a8b9113/EuDrZuQTW9m1phBXOsauz_EpJH3s8X.mp4",
    "width": 1280
  }
}

Endpoint: POST https://fal.run/xai/grok-imagine-video/extend-video Endpoint ID: xai/grok-imagine-video/extend-video

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "xai/grok-imagine-video/extend-video",
    arguments={
        "prompt": "The camera slowly zooms out to reveal the city skyline at sunset",
        "video_url": "https://v3b.fal.media/files/b/0a8b9112/V5Z_NIPE3ppMDWivNo6_q_video_019.mp4"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

Examples

Clouds timelapse there are mountains behind

Input Schema

prompt

string

required

Text description of what should happen next in the video.

video_url

string

required

URL of the source video to extend. Must be MP4 format (H.264, H.265, or AV1 codec), 2-15 seconds long.

duration

integer

default:"6"

Length of the extension in seconds. Default value: 6Range: 2 to 10

Output Schema

video

VideoFile

required

The extended video (original + extension stitched together).

Input Example

{
  "prompt": "The camera slowly zooms out to reveal the city skyline at sunset",
  "video_url": "https://v3b.fal.media/files/b/0a8b9112/V5Z_NIPE3ppMDWivNo6_q_video_019.mp4",
  "duration": 6
}

Output Example

{
  "video": {
    "content_type": "video/mp4",
    "duration": 16,
    "file_name": "extended_video.mp4",
    "fps": 24,
    "height": 720,
    "num_frames": 384,
    "url": "https://v3b.fal.media/files/b/0a8b9113/extended_video.mp4",
    "width": 1280
  }
}

Grok Imagine Video — Video Generation
Grok Imagine Reference to Video — Video Generation
Grok Imagine Extend Video — Video Generation

Limitations

duration range: 1 to 15
aspect_ratio restricted to: auto, 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16
resolution restricted to: 480p, 720p
aspect_ratio restricted to: 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16
duration range: 1 to 10
resolution restricted to: auto, 480p, 720p
duration range: 2 to 10

Video Generation

Image Generation

Audio

Vision

3D

Xai Grok Imagine Video API

Try it in the Playground

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Try it in the Playground

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Try it in the Playground

Quick Start

Examples

Input Schema

Output Schema

Input Example

Output Example

Try it in the Playground

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Try it in the Playground

Quick Start

Examples

Input Schema

Output Schema

Input Example

Output Example

Limitations

Video Generation

Image Generation

Audio

Vision

3D

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Examples

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Examples

​Input Schema

​Output Schema

​Input Example

​Output Example

​Related

​Limitations

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Examples

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Examples

Input Schema

Output Schema

Input Example

Output Example

Related

Limitations