Grok Imagine Video 1.5 Image to Video ComfyUI Official Example

The Grok Imagine Video 1.5 Partner Node enables high-quality video generation with native audio from an image or a text prompt. Powered by xAI’s latest Grok model, it produces realistic motion with synchronized audio and supports up to 1080p resolution. The node supports three model variants selected via its model parameter:

• grok-imagine-video: the previous generation model, supports optional image input
• grok-imagine-video-1.5: the full-quality 1.5 model, supports 1080p output
• grok-imagine-video-1.5-lite: a faster, lower-cost variant of 1.5 that generates from a text prompt or an image, with 480p, 720p, and 1080p output

All variants generate native audio: sound effects, ambience, and dialogue are synthesized in the same pass, with no separate audio pipeline needed. Video duration ranges from 1 to 15 seconds.

​

What Grok Imagine Video 1.5 is good at

• Image-to-video generation: produces high-quality video from a single input image
• Text-to-video generation: the grok-imagine-video-1.5-lite variant also generates from a text prompt alone
• Faster, lower-cost option: grok-imagine-video-1.5-lite runs at a lower per-second rate than 1.5
• Native audio: sound effects, ambience, and dialogue are synthesized in the same pass, with no separate audio pipeline needed
• Realistic motion: motion stays synchronized with the generated audio
• Up to 1080p output: the 1.5 models support 1080p resolution
• Flexible duration: video length from 1 to 15 seconds

​

Grok Imagine Video 1.5: Image to Video

​

Workflow Overview

This workflow uses three nodes:

• LoadImage: provides the starting image frame
• GrokVideoNode: the core node configured with the grok-imagine-video-1.5 model
• SaveVideo: saves the generated video with native audio

​

Steps to Run

1. Upload a starting image: use the LoadImage node to load your reference image
2. Enter your prompt: describe the motion, atmosphere, and scene dynamics in the GrokVideoNode node
3. Select model: ensure grok-imagine-video-1.5 is selected
4. Set resolution: choose output resolution (720p recommended)
5. Set duration: choose the video length in seconds
6. Set seed: control whether the node re-runs; outputs are not reproducible regardless of seed
7. Click Queue: press Ctrl+Enter to generate

​

Output

The generated video includes native audio synchronized with the motion, saved automatically via the SaveVideo node.

​

Tips

• Use high-quality input images for best results
• The prompt works best when it describes both the visual scene and the motion dynamics
• For different results, try varying the seed value

​

Grok Imagine Video 1.5 Lite

grok-imagine-video-1.5-lite is the faster, lower-cost variant of 1.5. It generates from a text prompt or a starting image and supports 480p, 720p, and 1080p output. Two templates cover it.

​

Lite text-to-video workflow

1. Select grok-imagine-video-1.5-lite as the model in the GrokVideoNode node
2. Enter a prompt describing the scene, motion, and sound
3. Set resolution (480p, 720p, or 1080p) and duration (1 to 15 seconds)
4. Click Queue to generate the video

​

Lite image-to-video workflow

1. Upload a starting image to the LoadImage node
2. Select grok-imagine-video-1.5-lite as the model in the GrokVideoNode node
3. Describe the motion in the prompt, then set resolution and duration
4. Click Queue to generate the video