GROK IMAGINE / TEXT + IMAGE TO VIDEO

Create video with Grok Imagine models

Use Grok Imagine for text-to-video or image-to-video with style control, or choose Grok Imagine 1.5 for image-led motion with automatic framing.

Content verification

Method: Model and workflow specifications are drawn from the current RedVideo configuration catalog. Live availability, supported settings, and generation quotes can change; confirm them in Studio before generating.

LIVE CATALOG FACTS

MODELS AND CAPABILITIES

Specifications below come from the workflows currently configured in RedVideo. Live availability and generation quotes remain visible in the studio.

VIDEO MODEL

Grok Imagine

Grok video generation from text or an image, with style control.

Workflows
Text to Video · Image to Video
Duration
6s · 10s · 15s
Output
720p
Audio
Model managed
Open model
VIDEO MODEL

Grok Imagine 1.5

Grok 1.5 image motion with automatic framing.

Workflows
Image to Video
Duration
6s · 10s · 15s
Output
720p
Audio
Model managed
Open model
TWO ROUTES

Start with a prompt or animate an existing frame

Grok Imagine supports text-to-video and image-to-video, with style control on the request. Grok Imagine 1.5 focuses on image-to-video and uses automatic framing.

The image-to-video prompt is optional for both routes. Adding a concise direction can still help describe subject movement, camera behavior, timing, and atmosphere.

  • Text-to-video and image-to-video on Grok Imagine
  • Image-to-video on Grok Imagine 1.5
  • Six-, ten-, and fifteen-second duration choices
OUTPUT CONTROLS

Frame the clip for landscape, portrait, or square

Both routes list 16:9, 9:16, and 1:1 ratios with 720p output settings. Available durations are 6, 10, and 15 seconds.

Audio is managed by the selected route rather than exposed as the same optional toggle used by some other model families. Review the generated clip for both visual and audio suitability.

CREATIVE DIRECTION

Prompt the movement rather than repeating the frame

When an image already defines the subject and composition, direct the change over time: action, camera, pace, environment, and mood. A prompt cannot guarantee preservation of identity, typography, or fine source details.

The studio shows current model access and the generation quote before submission. Provider, regional, and moderation constraints can still affect a request or result.

QUESTIONS, ANSWERED

FREQUENTLY ASKED QUESTIONS

Which Grok Imagine models are available in RedVideo?
The current catalog lists Grok Imagine and Grok Imagine 1.5.
Can Grok Imagine create video from text?
Grok Imagine supports text-to-video. Grok Imagine 1.5 is limited to image-to-video in the current catalog.
Do I need a prompt for Grok image-to-video?
A prompt is optional for image-to-video on both listed routes. A motion-focused prompt can provide more direction for the requested shot.
What duration and ratio options do Grok Imagine models provide?
Both routes list 6, 10, and 15 seconds with 16:9, 9:16, and 1:1 ratios.
Does every Grok Imagine request produce the same type of result?
No. Results vary with the route, source image, prompt, style, duration, and model response. Provider, regional, and moderation constraints can also apply.
OPEN REDVIDEO

BUILD THE FIRST GENERATION

Select the model and workflow that fit the idea, review the live settings and quote, then start creating.