What problem does it solve?
This Skill makes it possible to generate professional AI videos from text prompts or reference media, reducing manual production time and enabling rapid concept exploration.
Core Features & Use Cases
- Text-to-Video: Create videos from detailed textual descriptions, including dialogue, SFX, and ambient audio when using Veo 3.1.
- Image-to-Video: Animate a starting image into a living scene with motion and effects.
- Batch & Extensions: Generate multiple scenes in parallel and extend videos for longer narratives.
- Backends & Models: Supports Google Veo 3.1 and OpenAI Sora (and config options for duration, resolution, and aspect ratio) to fit various production needs.
Quick Start
Provide a concise video prompt and choose 1) a Veo model for text-to-video or image-to-video, 2) duration, 3) aspect ratio and resolution. Then run the script from the scripts directory, for example: <executable prompt> -p "A sunset over mountains" -d 8 -r 720p -a 16:9 (via Veo) or -p "A cinematic scene" -d 10 -r 1080p -a 16:9 (via Sora).