TypingMindTypingMindThe best frontend for AI
Image To Video Shots logo

Image To Video Shots

Community
xianyu110
image-to-video-shots

主图转视频：把一张或几张商品主图/白底图/场景图，写成可直接喂给图生视频模型的镜头提示词（运镜、主体动作、光线、时长、负面约束），并保证商品不变形。Use when the user has product images and wants a product video, 主图视频, 图生视频, image-to-video, animate a product photo, or 让主图动起来 — with any image-to-video model (Seedance / 可灵 Kling / Veo / Runway / Hailuo / Wan …) or a local Ken Burns fallback.

Overview

Publisherxianyu110
Repositoryecommerce-video-skills
Skill nameimage-to-video-shots
Stars
110
Forks
16
Bundled files
4
LicenseMIT
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by xianyu110 on GitHub. Read the source before you install it.

Installation

Install the Image To Video Shots AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/xianyu110/ecommerce-video-skills/tree/main/skills/image-to-video-shots
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/xianyu110/ecommerce-video-skills.git /tmp/ecommerce-video-skills
mkdir -p .claude/skills
cp -r /tmp/ecommerce-video-skills/skills/image-to-video-shots .claude/skills/image-to-video-shots
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Image To Video Shots in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Image To Video Shots on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Image To Video Shots is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

主图转视频 · Image → Video Shots

把静态商品图变成 3–6 秒的「会动的镜头」：每张图配一条图生视频提示词 + 一条本地兜底方案（ffmpeg Ken Burns），保证没有视频模型也能出片。

Part of ecommerce-video-skills · 图从哪来？用姊妹仓库 ecommerce-image-skills 先出白底图/场景图/卖点图。

输入 Inputs

必填说明
商品图 1–6 张白底主图、场景图、细节图均可；越清晰越好（≥1000px）
投放平台抖音 / TikTok Shop / 视频号 / 淘宝主图视频 / Amazon（决定画幅 9:16、1:1、3:4、16:9）
可选卖点（最多 3 条）、目标时长、风格（清爽 / 高级 / 活力）、可用的视频模型

步骤 Steps

  1. 商品一致性锁（必做）：看图写下形状、颜色、Logo/文字、材质、配件——之后每条提示词原样带上，禁止模型改商品。

    text
    PRODUCT LOCK: tall matte sage-green bottle, natural bamboo lid with black loop,
small white "AURA" wordmark on upper body. Keep shape, colour, logo and proportions identical in every frame.

  2. 给每张图选一个镜头角色（一张图只做一件事）：

    图类型推荐镜头动作
    白底主图缓慢推近 / 360° 环绕（模型支持时）产品静止，光影扫过
    场景图轻微横移 / 手部入画人物拿起、倒水、放进包里
    细节图微距推近光斑划过材质纹理
    卖点/信息图静止或极慢推不让文字变形（文字区域尽量不动）

  3. 写提示词（下方模板）：主体 → 动作 → 运镜 → 光线/氛围 → 时长/画幅 → 约束。动作越小，商品越稳。

  4. 每条镜头都给本地兜底：没有视频模型 / 模型把商品变形时，用 ffmpeg-auto-assemble 的 motion 字段（zoom_in / pan_left / punch …）直接让静图动起来。

  5. 交付：镜头表（编号、图、提示词、兜底 motion、时长）+ 可以直接粘进 storyboard.json 的 shots 片段。

提示词模板 Prompt templates

通用图生视频（中文）

text
[参考图] 作为首帧。{PRODUCT LOCK}
镜头：{缓慢推近 / 从左向右平移 / 低角度环绕 30°}，运动平稳，无抖动。
画面动作：{冰块落入杯中溅起细小水花 / 手从画面右侧入画拿起杯子 / 柔和光斑从左扫到右}。
光线：{明亮自然光 / 柔和棚拍光，浅景深}。
时长约 {4} 秒，{9:16} 竖屏。
要求：商品形状、颜色、Logo 与参考图完全一致；不新增文字；不出现其他品牌；手部自然、五指正常。

English (most models parse English best)

text
Use the reference image as the first frame. {PRODUCT LOCK}
Camera: {slow push-in | gentle left-to-right truck | 30° low-angle orbit}, smooth, no shake.
Action: {ice cubes drop into the bottle with a small splash | a hand enters from the right and lifts the bottle | a soft light sweep across the surface}.
Lighting: {bright natural daylight | soft studio light, shallow depth of field}.
About {4} seconds, {9:16} vertical.
Keep the product's shape, colour and logo identical to the reference. No new text, no other brands, natural hands.

首尾帧模式（模型支持首帧+尾帧时）：首帧 = 白底主图，尾帧 = 场景图，提示词只写「从棚拍过渡到户外场景，商品保持不变，镜头缓慢拉远」。

负面约束（模型支持 negative prompt 时）：deformed product, melting, extra logos, changed colour, warped text, extra fingers, flicker, watermark

本地兜底（无模型）

json
{"image": "assets/white-bg.webp", "motion": "zoom_in", "line": "换这只保温杯试试。"}
bash
python scripts/assemble.py storyboard.json -o out/main-video.mp4 --size 1080x1080   # 本目录已附带 assemble.py

检查清单 Checklist

  • 每条提示词都带 PRODUCT LOCK
  • 一个镜头只有一个主要动作；商品本身动作越少越好
  • 卖点图/带字图只用静止或极慢运镜
  • 画幅与平台一致（主图视频常用 1:1 / 3:4，信息流 9:16）
  • 不写模型不支持的参数；时长、分辨率以所用模型文档为准
  • 每个镜头都有本地 motion 兜底

常见问题与修复 Failure fixes

问题修复
商品变形 / Logo 糊掉减少动作，改成「camera moves, product stays still」；或改用本地 Ken Burns
手部畸形去掉手部动作，或让手只出现半秒、在画面边缘
画面闪烁缩短时长、降低运动幅度、关掉夸张光效
文字乱码别让模型生成文字；字幕和花字交给 subtitles-and-text-effects 后期加
颜色漂移在提示词里写出色值或颜色名，并要求 "match the reference colour exactly"

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Image To Video Shots AI skill do?

主图转视频：把一张或几张商品主图/白底图/场景图，写成可直接喂给图生视频模型的镜头提示词（运镜、主体动作、光线、时长、负面约束），并保证商品不变形。Use when the user has product images and wants a product video, 主图视频, 图生视频, image-to-video, animate a product photo, or 让主图动起来 — with any image-to-video model (Seedance / 可灵 Kling / Veo / Runway / Hailuo / Wan …) or a local Ken Burns fallback.

Why use Image To Video Shots on TypingMind?

Because you install it once and use it with any model. Image To Video Shots is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Image To Video Shots in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/xianyu110/ecommerce-video-skills/tree/main/skills/image-to-video-shots. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Image To Video Shots?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Image To Video Shots?

As many as you like. As long as a model supports skills, you can use Image To Video Shots with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Image To Video Shots AI skill free?

Yes. It is published on GitHub by xianyu110 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
affaan-m logo

Video Editing

affaan-m
CommunityPopular

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in…

40.4K
270.2K
1 files
View
NousResearch logo

Ai Presenter Video

NousResearch
OrganizationPopular

Make a verified AI presenter video from script + image.

53.5K
250.4K
7 files
View
NousResearch logo

Audiocraft Audio Generation

NousResearch
OrganizationPopular

AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.

53.5K
250.4K
2 files
View
NousResearch logo

Brag Slim

NousResearch
OrganizationPopular

Launch video from a project or URL, upstream-maintained.

53.5K
250.4K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇