grok-media

Generate and edit images and create videos using xAI Grok API.

Updated May 23, 2026
One-click install
npx skills add https://github.com/xingBaGan/FANovelist --skill grok-media-xingbagan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: grok-media
Source: https://github.com/xingBaGan/FANovelist/tree/main/src/openharness/openmontage/agents_skills/grok-media
Command: npx skills add https://github.com/xingBaGan/FANovelist --skill grok-media-xingbagan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a guide for using xAI Grok to generate and edit images, and create videos, covering authentication, endpoints, prompt structure, and async polling.

Core Features & Use Cases

  • Image Generation: Create images from text prompts.
  • Image Editing: Modify existing images with specific changes.
  • Video Creation: Generate videos from text, images, or reference images.
  • Use Case: Use this Skill to create a video featuring a character wearing a specific jacket, sourced from an image, and describe the scene in detail.

Quick Start

Generate a video with the following prompt: "Create a video where a person from <IMAGE_1> wears a jacket from <IMAGE_2> and performs an action in a setting described as <IMAGE_3>".

Frequently Asked Questions about grok-media

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images from text prompts using xAI Grok?

To generate images from text prompts using xAI Grok, you need to authenticate with an xAI API key and send your request to the designated image generation endpoints, providing descriptive text prompts to produce the visual output.

Can I create videos from text and reference images with xAI Grok?

Yes, you can create videos from text, images, and reference images using xAI Grok by calling the video creation endpoints, which requires API key authentication and asynchronous polling to retrieve the final video result.

How do I edit existing images with xAI Grok?

You can edit existing images by sending the target image to the xAI Grok image editing endpoints with specific modification instructions, requiring your xAI API key for authentication to process the requested changes.

Do I need an xAI API key to use Grok for media production?

Yes, an xAI API key is required for authentication before you can access the endpoints for image generation, image editing, and video creation using xAI Grok within your media production workflow.

How does asynchronous polling work for xAI Grok video creation?

Asynchronous polling for xAI Grok video creation involves sending an initial request to the video endpoints and then repeatedly checking the status until the process completes, allowing you to retrieve the generated video.

Can I combine multiple reference images to generate a single video?

Yes, you can combine multiple reference images to generate a single video by structuring your prompt to reference distinct images, such as using a person from one image and a jacket from another to define the scene.