A Six-Layer Framework for Prompting AI Video Models
Venice AI breaks a video prompt into six layers: subject and action, shot type, camera movement, lighting, technical specs and pacing. It also shares three ways to iterate that save credits across models like Kling, Sora, Wan and Veo.
Key points
- Vague prompts are the most common cause of weak results
- Shot size and angle set the feel: low angle reads powerful, high angle vulnerable
- Name the light: golden hour, blue hour, soft or hard
- Lens and film-stock terms: 35mm, 85mm, shallow depth of field, film grain
- A reusable prompt template