Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
bytedance avatar

Image Video Gen

  • 70 installs
  • 411 repo stars
  • Updated August 4, 2026
  • bytedance/agentkit-samples

Image Video Gen is a Claude skill (ByteDance AgentKit sample) workflow that orchestrates web-search, image-generate and video-generate to turn a text description into storyboard images and an optional video.

About

Image Video Gen is a ByteDance AgentKit workflow skill that turns a text description into storyboard images and optionally a video. It coordinates the byted-web-search, image-generate and video-generate skills: it gathers background info, generates storyboard images, then optionally generates video. It has no executable script and works only by orchestrating those atomic skills.

  • Workflow that orchestrates web-search, image and video generation
  • Turns a text description into storyboard images and optional video
  • Coordinates atomic skills; no executable script of its own

Image Video Gen by the numbers

  • 70 all-time installs (skills.sh)
  • Ranked #848 of 1,335 Generative Media skills by installs in the Skillselion catalog
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
At a glance

image-video-gen capabilities & compatibility

Capabilities
image generation · video generation · storyboard generation
Use cases
image generation · video generation
Pricing
Free
From the docs

What image-video-gen says it does

这是一个用于生成图片和视频的智能体工作流。它协调 `byted-web-search`, `image-generate`, 和 `video-generate` 工具来完成任务。
SKILL.md
此技能本身没有 Python 执行脚本 (`scripts/` 目录下无脚本)。
SKILL.md
根据准备好的背景信息,调用 `image-generate` 工具生成分镜图片。
SKILL.md
npx skills add https://github.com/bytedance/agentkit-samples --skill image-video-gen

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs70
repo stars411
Last updatedAugust 4, 2026
Repositorybytedance/agentkit-samples

What it does

Turn a text description into storyboard images and an optional generated video.

Who is it for?

Generating storyboard images and an optional video from a text prompt via a single orchestrated flow.

Skip if: Running standalone; it has no script and depends on image-generate and video-generate.

When should I use this skill?

You want to turn a story or description into storyboard images and optionally a video.

What you get

Storyboard images (and an optional video) generated from a single text description.

  • storyboard image list (Markdown)
  • optional generated video

By the numbers

  • depends on 3 atomic skills
  • calls web-search at most 2 times per docs

Files

SKILL.mdMarkdownGitHub ↗

Image Video Tool Workflow

描述

这是一个用于生成图片和视频的智能体工作流。它协调 byted-web-search, image-generate, 和 video-generate 工具来完成任务。

依赖技能

  • byted-web-search
  • image-generate
  • video-generate

工作流程

1. 理解用户意图

  • 接收用户输入的文本描述。
  • 如果用户输入是故事或情节,直接调用 byted-web-search 工具获取背景信息。
  • 如果用户输入为其他类型(如问题、请求),则先调用 byted-web-search 工具 (最多调用2次),找到合适的信息。

2. 生成图片

  • 根据准备好的背景信息,调用 image-generate 工具生成分镜图片。
  • 生成后,以 Markdown 图片列表形式返回,例如:
   ![分镜图片1](https://example.com/image1.png)

3. 生成视频 (可选):

  • 根据用户输入,判断是否需要调用 video-generate 工具生成视频。
  • 返回视频 URL 时,使用 Markdown 视频链接列表,例如:
   <video src="https://example.com/video1.mp4" width="640" controls>分镜视频1</video>

注意事项

  • 此技能本身没有 Python 执行脚本 (scripts/ 目录下无脚本)。
  • 它通过协调其他原子技能来工作。
  • 输入输出中,任何涉及图片或视频的链接 url,绝对禁止任何形式的修改、截断、拼接或替换,必须 100% 保持原始内容的完整性与准确性。

Related skills

FAQ

Does this skill have its own script?

No. The docs state it has no Python execution script and works by coordinating other atomic skills.

Which skills does it depend on?

byted-web-search, image-generate and video-generate.

Generative Mediaagentsautomationllm

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.