image-video-gen

Coordinate web-search, image-generate, and video-generate tools to create storyboard images and videos.

417|87|Updated Nov 12, 2025
One-click install
npx skills add https://github.com/bytedance/agentkit-samples --skill image-video-gen
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: image-video-gen
Source: https://github.com/bytedance/agentkit-samples/tree/main/skills/image-video-gen
Command: npx skills add https://github.com/bytedance/agentkit-samples --skill image-video-gen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

通过协调 web-search、image-generate 与 video-generate 等原子技能,本技能提供一个端到端的工作流,将文字描述自动转化为可视的分镜图片与视频,降低多步骤整合的工作量。

Core Features & Use Cases

  • 工作流协调:将文本描述转化为分镜图片的生成流程,并在需要时触发视频生成。
  • 依赖整合:无缝对接 web-search、image-generate、video-generate 等原子技能,提供一致的使用体验。
  • Use Case: 广告与教育内容创作场景下,快速将故事线转化为可视化素材(图片序列和视频)。

Quick Start

输入一个文本描述,系统将协调相关原子技能生成分镜图片并(如需)生成视频。

Frequently Asked Questions about image-video-gen

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

FAQPage Schema
How do I generate storyboard images and videos from text prompts?

You can generate storyboard images and videos from text prompts by inputting a text description; the system then coordinates web-search, image-generate, and video-generate tools to automatically transform the text into visual content.

What is the best way to coordinate text-to-media generation for marketing content?

The best way to coordinate text-to-media generation for marketing is using a workflow that integrates web-search, image-generate, and video-generate tools to transform storylines into visual materials without running local scripts.

Do I need local scripts to orchestrate image and video generation?

No, you do not need local scripts to orchestrate image and video generation. The system coordinates web-search, image-generate, and video-generate tools directly to deliver visuals without running local scripts.

Can I use this workflow to create educational content from a storyline?

Yes, you can use this workflow to create educational content from a storyline. It transforms textual prompts into storyboard images and optional videos, making it suitable for educational content creation.

Does the image and video generation workflow support web search integration?

Yes, the image and video generation workflow supports web search integration. It coordinates web-search alongside image-generate and video-generate atomic skills to deliver visuals based on your prompts.

What are the limitations of orchestrating text-to-media prompts for storyboards?

A limitation of orchestrating text-to-media prompts for storyboards is that the output relies on the coordinated atomic skills, meaning visual quality and accuracy depend entirely on the underlying image-generate and video-generate tools.