Can I generate multiple videos at the same time?

Yes, the skill supports batch generation via a scenes.json file, allowing you to process multiple video prompts in parallel to save time.

How do I ensure visual continuity between different video clips?

The skill includes a video extension feature that uses a previous Veo-generated video as a reference to continue the action, maintaining consistent characters and settings.

Does this skill support animating my existing images?

Yes, the image-to-video capability allows you to provide a local image path to be used as the starting frame for your generated video.

Can I generate videos with sound and dialogue?

Yes, when using Google Veo 3.1 models, you can include dialogue in quotes and describe sound effects or ambient audio directly within your prompt.

Which AI models are supported for video generation?

This skill supports Google Veo 3.1 (default), Veo 3.1-fast for quicker iterations, and OpenAI Sora for creative, long-form videos up to 20 seconds.

AI Video Generation

Name: AI Video Generation
Author: michaelboeding

bymichaelboeding

•

内容管理

Generates high-quality AI videos with synchronized audio, dialogue, and seamless motion using Google Veo 3.1 and OpenAI Sora.

The Video Generation skill empowers developers and creators to generate cinematic AI videos directly from Claude using industry-leading models like Google Veo 3.1 and OpenAI Sora. It features a comprehensive workflow for text-to-video and image-to-video generation, including the ability to generate native audio, dialogue, and sound effects. Advanced capabilities like video extension allow for true visual continuity in long-form projects, while parallel batch processing enables the generation of multiple scenes simultaneously, making it an essential tool for rapid content prototyping and production within the AI agent environment.

主要功能

01Advanced image-to-video animation and reference image guidance

029 GitHub stars

03Multi-model support featuring Google Veo 3.1 and OpenAI Sora

04Integrated audio generation for dialogue, SFX, and ambient soundscapes

05Video extension capabilities for creating seamless long-form continuity

06High-speed parallel batch generation for multi-scene workflows

使用场景

01Generating long-form narrative content by extending scenes with visual continuity

02Animating static UI/UX mockups or concept art into dynamic video demonstrations

03Creating cinematic marketing assets and social media clips from text descriptions

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add michaelboeding/skills video-generation

For use in Claude.ai and ChatGPT

Download Skill