| license | Apache-2.0 |
| name | ai-video-production-master |
| description | Expert in script-to-video production pipelines for Apple Silicon Macs. Specializes in hybrid local/cloud workflows, LoRA training for character consistency, motion graphics generation, and artist commissioning. Activate on 'AI video production', 'script to video', 'video generation pipeline', 'character consistency', 'LoRA training', 'cloud GPU', 'motion graphics', 'Wan I2V', 'InVideo alternative'. NOT for real-time video editing, video compositing (use DaVinci/Premiere), audio production, or 3D modeling (use Blender/Maya). |
| allowed-tools | Read,Write,Edit,Bash(python:*,ffmpeg:*,npm:*),WebFetch,mcp__firecrawl__firecrawl_search |
| category | Video & Audio |
| tags | ["video-production","ai","automation","content-creation","editing"] |
| pairs-with | [{"skill":"sound-engineer","reason":"Audio for AI-generated videos"},{"skill":"voice-audio-engineer","reason":"Voice synthesis for narration"}] |
AI Video Production Master
Expert in script-to-video production pipelines for Apple Silicon Macs. Specializes in hybrid local/cloud workflows, style consistency, and motion graphics generation.
DECISION POINTS
Method Selection Tree
Script Analysis:
├── Content Type = Educational/Corporate/Documentary
│ ├── Budget < $50/month → Stock Footage Assembly (InVideo-style)
│ └── Budget > $50/month → Stock + T2V Hybrid
├── Content Type = Creative/Artistic/Abstract
│ ├── Timeline < 2 days → Sora/Runway T2V
│ └── Timeline > 2 days → Custom I2V with LoRA training
└── Content Type = Brand/Character-focused
├── Existing assets available → I2V animation pipeline
└── No assets → Commission artists → I2V pipeline
Quality vs. Cost Decision:
├── Professional deliverable needed
│ ├── Use Sora/Runway Gen-3 (premium T2V)
│ └── Commission custom artwork for I2V
├── Prototype/test content
│ ├── Use stock footage + free T2V models
│ └── Local ComfyUI I2V generation
└── High volume production
├── Cloud batch processing (Vast.ai)
└── Automated stock footage workflows
Error Recovery Tree:
├── Quality fails at T2V generation
│ ├── Switch to stock footage + motion graphics overlay
│ └── Fallback to I2V with commissioned artwork
├── Cloud GPU timeout/failure
│ ├── Retry with different provider (Vast.ai → RunPod)
│ └── Switch to local processing with extended timeline
└── Style consistency breaks
├── Retrain LoRA with more reference images
└── Use IPAdapter + consistent prompt structure
Processing Location Decision Matrix
| Shot Count | Complexity | Budget | Recommendation |
|---|
| 1-5 | Simple | Any | Local M4 Max |
| 6-20 | Medium | <$10 | Stock footage |
| 6-20 | High | >$10 | Cloud GPU batch |
| 20+ | Any | Any | Cloud GPU required |
FAILURE MODES
Blurry Motion Jitter
Symptoms: Inconsistent frame rates, stuttering motion, temporal artifacts
Diagnosis: Mismatched FPS settings or insufficient motion guidance
Fix: Set consistent 24fps pipeline, add motion strength controls, use higher guidance scale (7-9)
Detection Rule: If temporal consistency score < 0.7 or frame delta > 0.3, apply motion stabilization
Character Consistency Drift
Symptoms: Character appearance changes between shots, style inconsistency
Diagnosis: Insufficient reference conditioning or LoRA overfitting
Retrain LoRA with 15-20 reference images, use IPAdapter for face consistency
If character similarity score < 0.8 between consecutive shots, halt and retrain
