Skip to main content

Grok Imagine 1.5 Video is a third-party video generation model from xAI, available in Runway. It generates video from a text prompt, with optional first-frame images, image references and audio references to shape the look and sound of your output.

This article covers how to access Grok Imagine 1.5 Video in Custom, which inputs and settings are available, and how credit cost is calculated.


Spec Information

Duration Up to 15 seconds
Aspect ratio 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3
Output resolutions 480p, 720p, 1080p
1080p is only supported for Text to Video and First frame to Video
Supported inputs Text, Image, Audio
Modalities Text to Video
Image to Video
Credit cost 480p — 10 credits per second
720p — 16 credits per second
1080p — 29 credits per second
+1 credit per reference or first-frame image
Input requirements First-frame image Reference image Reference audio
Maximum inputs 1 7 1

Step 1 – Selecting Grok Imagine 1.5 Video

The model picker lives at the bottom of the generation panel. Grok Imagine 1.5 Video is available in Custom, Workflows, and Apps, and is not available in Agent or Agent-driven Workflows.

  1. From the left sidebar, click Custom.
  2. Select the Video tab at the top of the generation panel.
  3. Click the model dropdown at the bottom of the panel and choose Grok Imagine 1.5 Video.

Step 2 — Adding the Inputs

Grok Imagine 1.5 Video requires a text prompt and three optional media references. See the Spec Information table above for input limits, resolutions and credit costs.

  • Text prompt — describe the scene, subjects, action and mood you want; be specific about camera movement, lighting and pacing
  • First-frame image (optional) — upload a single image to set the opening frame of your video
  • Image references (optional) — add up to 7 images to guide the style, subjects or composition; not supported at 1080p, so choose 480p or 720p
  • Audio reference (optional) — add 1 audio file to guide the generation; not supported at 1080p

Note: When you include any image or audio reference, your text prompt should describe how the references should be used. Some input combinations are not allowed; the interface shows which options are compatible with your current selections, so adjust your inputs or resolution if a selection is unavailable.


Step 3 — Generating your video

With your prompt and inputs in place, choose your output settings below the prompt box:

  • Aspect ratio — 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3
  • Resolution480p, 720p or 1080p; 1080p is only available for Text to Video and First frame to Video
  • Duration — up to 15 seconds

Your resolution and duration set the credit cost, plus 1 credit per reference or first-frame image.

Once your settings are ready, select Generate.


Next Steps

Now that you know how to generate with Grok Imagine 1.5 Video, take your output further in Runway:

  • Assemble a cut in Agent — bring your clips into Runway Agent to sequence, trim and arrange them in the timeline editor
  • Edit your result with Aleph 2.0 — restyle scenes, swap elements or adjust lighting with text prompts in Edit Studio; see the Aleph 2.0 Prompting Guide for techniques
  • Upscale for delivery — reference-guided generations are capped at 720p, so generate with references, then use the Upscale App to bring your final version up to 4K