Video Gen Prompt Framework: Complete Guide with Examples (2026)

Last updated June 28, 2026 · 1 example · Works with ChatGPT, Claude, Gemini
Quick Answer

Video Gen is an eight-field framework for AI video generation: Scene describes what to depict, Motion specifies how things move, Camera controls camera movement, Lighting sets illumination, Style defines the aesthetic, Duration sets clip length, Negative lists exclusions, and Parameters adds model-specific flags. Works with Sora, Runway Gen-3, Pika, Kling, and Wan.

What Is the Video Gen Prompt Framework?

Video generation prompts add two critical dimensions over image prompts: Motion and Camera. Motion describes how subjects move within the frame. Camera describes how the camera itself moves. These two fields transform a static image description into a dynamic sequence. Getting them right is the difference between a compelling clip and a video that looks like a jittery photo.

What Does Video Gen Stand For?

Structured template for Sora, Runway, Pika, and Kling.

Sc
Scene
What is depicted — subjects, environment, time of day, key visual elements.
Mo
Motion
How elements within the frame move — characters walking, water flowing, objects rotating. Internal movement.
Ca
Camera
Camera movement — static, slow push in, dolly left, arc around subject, handheld, aerial descent.
L
Lighting
Illumination type — golden hour, studio, neon, moonlit, dramatic side lighting.
St
Style
Visual aesthetic — cinematic 4K, anime, documentary, vintage film, hyperrealistic.
D
Duration
Clip length in seconds. Most models produce best quality at 4–6 seconds.
N
Negative
What to exclude — flickering, artifacts, watermark, sudden cuts, morphing faces.
P
Parameters
Model-specific flags — resolution, frame rate, seed, motion strength.

When to Use Video Gen

Use Video Gen for any AI video generation task. For static images, use the Image Gen framework.

Video Gen Examples

Product demo clip
Scene: A dark minimal web application with glowing teal bubble nodes floating and slowly orbiting each other against a deep space background.
Motion: Bubbles gently pulse and drift, occasionally connecting with thin glowing lines. One bubble expands slightly as if being clicked.
Camera: Slow push in, starting wide and gradually closing to a medium shot over 6 seconds. Slight camera rotation adds depth.
Lighting: Deep dark background, teal and purple neon glow from the bubbles, subtle lens bokeh.
Style: Cinematic 4K, premium dark UI aesthetic, similar to Vercel or Linear product videos.
Duration: 6 seconds
Negative: Flickering, artifacts, abrupt cuts, text, watermark, faces, people.
Parameters: 1080p, 24fps, motion_strength: 0.6

Video Gen vs Other Frameworks

Video Gen vs Image Gen: Image Gen has 7 fields for static images. Video Gen adds Motion and Camera for video output. Always use Video Gen for video generation — the Motion and Camera fields are essential.

Use this Video Gen template in Promptary — free

Save your first Video Gen prompt in the structured editor and get a permanent REST API endpoint. Personal plan is free forever, no credit card required.

Start free

Frequently Asked Questions

What AI video generators work with this framework?

Video Gen works with Sora (OpenAI), Runway Gen-3 Alpha, Pika 2.0, Kling 1.6, Wan 2.1, and Luma Dream Machine. The Parameters field handles model-specific settings.

What is the difference between Motion and Camera?

Motion describes movement happening within the frame — a person walking, water flowing. Camera describes the movement of the camera itself — pushing in, panning, orbiting. Both are needed for compelling video prompts.

How long should AI video clips be?

Most models produce best quality at 4–6 seconds. Start with 5–6 seconds and extend once you have a working prompt.