Model icon
grok-imagine-video-1.5
Text to Video
Image to Video
Reference to Video
Model:
14.5 credits/per second

Input

grok-imagine-video-1.5
115/4096
image_urls 1

Optional: upload exactly one first-frame image.

Optional: upload 1–7 images and reference them as <IMAGE_0>, <IMAGE_1>, etc.

6s

Not available when image_urls is provided.

Estimated usage: 152 credits

Output

Example Output

This is sample data. Generate your own video to see real results.

Task: GROK-IMAGINE-VIDEO-15-EXAMPLE

Status: finished

Progress: 100%

Grok Imagine Video 1.5 API

Create videos from text, animate one first-frame image, or guide a scene with up to seven reference images. Choose 480p, 720p, or 1080p output and control clips from 1 to 15 seconds.

Three Video Workflows in One Model

Text to Video

Describe the scene, action, camera movement, and atmosphere without supplying an image.

Image to Video

Use one image as the first frame and prompt the motion that should follow.

Reference to Video

Supply up to seven references for subjects, characters, objects, or visual direction.

Grok Imagine Video 1.5 Features

Flexible inputs, directed movement, and practical output controls for short-form video workflows.

Animate a Strong First Frame

Keep a prepared image as the opening frame while the prompt directs subject action, object motion, and camera movement. This is useful for product concepts, character shots, and campaign drafts.

  • Exactly one first-frame image
  • Prompt-directed motion and camera cues
  • 480p, 720p, or 1080p output

Direct Camera Movement and Scene Rhythm

Describe tracking, push-ins, rising shots, subject movement, and environmental effects in natural language to turn a static concept into a directed scene.

  • Natural-language camera direction
  • Clip duration from 1 to 15 seconds
  • Seven landscape and portrait aspect ratios

Maintain Visual References Across a Shot

Reference mode accepts one to seven images. Mention them as <IMAGE_0>, <IMAGE_1>, and so on to describe how subjects and visual references should appear in the generated clip.

  • Up to seven ordered references
  • 480p and 720p reference output
  • Useful for recurring characters and art direction

What You Can Build

Product Motion

Turn catalog frames and product concepts into short moving previews.

Storyboard Tests

Preview camera movement and scene timing before committing to production.

Campaign Variations

Create multiple short-form motion concepts for ads and social channels.

Character Scenes

Use ordered references to guide recurring subjects and visual identity.

Grok Imagine Video 1.5 Generation Modes

CapabilityTextFirst FrameReference
Image inputNoneExactly 11–7
Resolution480p–1080p480p–1080p480p–720p
Aspect ratio controlYesUses source frameYes
Duration1–15s1–15s1–15s

How to Use Grok Imagine Video 1.5 on Vidgo API

Step 1: Create an API key
Get your key from the Vidgo API dashboard.

Step 2: Choose a workflow
Send only a prompt for text-to-video, one image_urls item for first-frame animation, or 1–7 reference_image_urls items for reference mode.

Step 3: Submit and retrieve the result
Use the returned task ID to poll status, or provide a callback URL for asynchronous delivery. View the API documentation.

Grok Imagine Video 1.5 Pricing

480p costs 14.5 credits per second, 720p costs 25 credits per second, and 1080p costs 45 credits per second. Each submitted input or reference image adds 2 credits.

Grok Imagine Video 1.5 API FAQ

Which inputs does Grok Imagine Video 1.5 support?

It supports text-only generation, one first-frame image, or 1–7 ordered reference images. The two image fields cannot be combined.

How long can generated videos be?

Set any whole-number duration from 1 to 15 seconds. The default is 6 seconds for text and first-frame modes, and 8 seconds for reference mode.

Can reference mode generate 1080p video?

No. Reference-to-video supports 480p and 720p. Text and first-frame image modes also support 1080p.

How do I receive the completed video?

Poll the status endpoint with the returned task ID or provide a callback URL when submitting the task.

How is usage calculated?

Output is charged per second according to resolution, plus 2 credits for each submitted input or reference image.

Why Use Vidgo API

One Consistent Endpoint

Use the same asynchronous submit and status flow as other Vidgo video models.

Practical Controls

Set workflow, resolution, duration, aspect ratio, and ordered references directly.

Transparent Usage

See the estimated credit cost before running a generation.

Production Delivery

Poll task status or use a callback URL to connect results to backend workflows.