video-motion

Generate Kling 3.0 and Veo 3 prompts to animate Nano Banana 2 images into motion videos.

1|Updated Mar 22, 2026
One-click install
npx skills add https://github.com/quocduvp/nanobanana2-skills --skill video-motion
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: video-motion
Source: https://github.com/quocduvp/nanobanana2-skills/tree/main/skills/video-motion
Command: npx skills add https://github.com/quocduvp/nanobanana2-skills --skill video-motion

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill generates Kling 3.0 and Veo 3 prompts to turn Nano Banana 2 images into motion videos, enabling rapid creation of branded motion content from static visuals.

Core Features & Use Cases

  • Kling 3.0 prompts for precise camera control, multi-shot sequences, and product reveals.
  • Veo 3 prompts for narrative-driven, audio-enabled brand storytelling.
  • Templates with negative prompts and audio directions for common video types (product reveals, fashion, skincare, unboxing) and practical usage guidance.

Quick Start

Describe your vision in English or Vietnamese and the skill will generate Kling 3.0 and Veo 3 prompts automatically.

Frequently Asked Questions about video-motion

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

FAQPage Schema
How do I generate Kling 3.0 prompts to animate a still product image?

To generate Kling 3.0 prompts for animating a still product image, describe your vision in English or Vietnamese to receive field-tested templates with precise camera controls, multi-shot sequences, and explicit negative prompts for product reveals.

Can I create audio-enabled brand story videos using Veo 3 prompts?

Yes, you can create audio-enabled brand story videos using Veo 3 prompts, which provide narrative-driven templates equipped with specific audio directions to standardize your short-form marketing content.

What is the best way to turn static fashion visuals into motion videos?

The best way to turn static fashion visuals into motion videos is using standardized Kling 3.0 and Veo 3 prompt templates tailored for fashion looks, ensuring consistent camera-movement vocabulary across your clips.

Does this prompt generation skill support Vietnamese input descriptions?

Yes, this prompt generation skill supports Vietnamese input descriptions, allowing you to describe your creative vision in either English or Vietnamese to automatically generate the required Kling 3.0 and Veo 3 prompts.

Why do my AI image-to-video generations include unwanted visual artifacts?

Your AI image-to-video generations may include unwanted visual artifacts due to missing negative prompts; this skill supplies explicit negative prompts to prevent anomalies and standardize high-quality motion output.