ai-video-generation
Generate AI Videos with Top Models
Also available from: halt-catch-fire,inference-sh-9,inference-sh,inference-shell,inference-sh-skills,inference-skills,inferen-sh,doany-ai,danielgwilson,inference-sh-8,infsh-skills,skillssh,skills-shell,qu-skills,agentspace-so,tool-belt,toolshell,tul-sh
Creating AI videos requires navigating multiple models with different capabilities and pricing. This skill routes your request to the optimal model based on your needs.
Download the skill ZIP
Upload in Claude
Go to Settings → Capabilities → Skills → Upload skill
Toggle on and start using
Test it
Using "ai-video-generation". Generate a video of a red kite tumbling across a beach at sunset
Expected outcome:
A 10-second 1080p video with HappyHorse 1.0: a red kite tumbles across a windswept beach at golden hour. Kids chase it laughing in the background. Wind and distant laughter audio generated in-pass.
Using "ai-video-generation". Animate this product image with a 180-degree rotation
Expected outcome:
A Veo 3-1 video: A product rotates 180 degrees on a marble surface with soft daylight. No other motion. 8 seconds, 720p.
Security Audit
SafeThis skill is a markdown documentation file that describes how to use the runcomfy CLI for AI video generation. All 210 static scanner findings are FALSE POSITIVES: backtick patterns are markdown code formatting, URL references are documentation links, and 'weak crypto' detections are YAML frontmatter misidentification. No shell injection surface exists since prompts pass via JSON strings. Network access is limited to RunComfy API endpoints only.
Risk Factors
⚙️ External commands (117)
🌐 Network access (61)
Quality Score
What You Can Build
Social Media Content Creation
Create vertical video clips for TikTok or Instagram Reels from text prompts with built-in audio. HappyHorse 1.0 generates synchronized audio in-pass for ready-to-post content.
Product Visualization
Animate product images with physics-accurate motion using Veo 3-1. Describe exact rotation degrees and object behavior for consistent brand presentation.
Cinematic Ad Production
Produce high-quality 4K video ads using Seedance v2 with multi-reference composition. Combine subject images, scene references, and style guides in one generation.
Try These Prompts
Generate a video of [describe the scene and action you want]. Use the best model for quality.
Animate this image: [describe image or provide URL]. Motion: [describe what should happen]. Duration: [X] seconds. Aspect ratio: [16:9 or 9:16].
Create a video where the subject syncs to this audio: [audio URL]. Scene description: [describe the setting and speaker]. Duration: [X] seconds.
Create a cinematic video using Seedance v2. Subject from [ref image]. Mood from [ref video]. Style: [lens type, color grade]. Duration: [X] seconds.
Best Practices
- Lead with subject and action verb: say 'a kite tumbles' not 'beautiful kite flying'
- Describe audio inline for models that support it: 'Audio: wind, footsteps, city ambiance'
- Match aspect ratio to delivery platform: 9:16 for vertical social, 16:9 for YouTube, 21:9 for cinematic
- Start with the default HappyHorse 1.0 for general use, upgrade to specialized models only when needed
Avoid
- Do not stack adjectives without action: 'a beautiful serene peaceful mountain' generates static scenes
- Do not describe audio in prompts for models that do not support in-pass audio (check model capabilities)
- Do not request extreme durations beyond model limits (typically 5-15 seconds per clip)