NamerynVideo Prompt Generator
Type who is on screen and what they do, pick the shot, the camera move, the light and the look, and copy a prompt laid out for Gemini Omni Flash, Veo 3.1, Kling 4.0 or Runway Gen-4.5. Every word in the prompt is yours apart from a few fixed labels; nothing leaves your browser.
Four Models, Four Suggested Layouts
The order of the parts is Nameryn's suggestion; makers say a clear description matters more than any order. The lengths and frame shapes are the ones each maker lists, checked on October 22, 2026.
- Gemini Omni Flash, in the Gemini app, Flow and the Gemini API, gets a scene line first, then a Cinematography block with the camera shot, the lighting and the style. Google asks for scene, camera movement, lighting and mood. Flow lists clips of 4, 6, 8 or 10 seconds in landscape or portrait, from text or from frames (Flow models, Gemini API).
- Veo 3.1, in Flow and on Google Cloud, gets one shot-list sentence that opens on the camera, then the subject and the action, then the look. It makes clips of 4, 6 or 8 seconds in 16:9 or 9:16, from text or a first frame (Veo 3.1 model page). Google closed the Veo 3.1 previews in the Gemini API on October 22, 2026.
- Kling 4.0, in the Kling app, gets the subject and its movement first, then the camera, the light and the style. It makes clips of 3 to 30 seconds in 16:9, 9:16, 1:1 or 21:9; started from an image, the clip takes the image's shape (Kling 4.0 guide). The Flash version stops at 20 seconds.
- Runway Gen-4.5, in the Runway web app, gets the camera first, then what moves in frame, the structure Runway suggests to new users. It makes clips of 2 to 10 seconds; from text only in 16:9, from an image in six shapes from 9:16 to 21:9 (Gen-4.5 help).
Sora is no longer offered: OpenAI closed the Sora app on April 26, 2026 and its API on September 24, 2026 (OpenAI). Apps change their settings often: if yours shows other values, set those in the app. The prompt works without them.
Your Words, Nothing Else
The prompt holds what you typed and picked, joined by fixed labels: Cinematography, Camera shot, Camera, Lighting, Style, Duration with its "seconds", and Aspect ratio. Nameryn adds no sentence of its own, no "cinematic, award-winning" padding and no hidden instruction. A field you leave empty drops out with its label. Nothing you type is sent anywhere or saved.
How to Write an AI Video Prompt Here
- Pick the model you will paste into, and whether you start from text or an image.
- Say who and what: one subject and one action, such as a red fox in fresh snow that pounces into a drift.
- Direct the camera: a shot and one camera move. One move per clip reads cleaner than three.
- Set the look: a few words of lighting and style.
- Copy the prompt, then set the same length and frame shape in the app. The guide to AI video prompts covers the rest.
Frequently Asked Questions
Why does the prompt change when I switch models?
The words stay yours; only the order and the labels change. Each layout is a suggestion, not a rule the model needs: Gemini Omni Flash gets a scene line and then a cinematography block, Veo 3.1 one shot-list sentence that opens on the camera, Kling 4.0 the subject and its movement before the camera, and Runway Gen-4.5 the camera first, the structure Runway suggests to new users.
Does the length in the prompt set the length of the clip?
No. Each app sets length and frame shape in its own settings. The prompt names them so the model plans the motion for that length; set the same values in the app before you render.
Does Nameryn add words to my prompt?
Only fixed labels such as Camera, Lighting, Style, Duration and Aspect ratio. Every other word is one you typed or picked. Nothing is sent anywhere or saved.
Can I use it for image-to-video?
Yes. Pick An image under Start from and the lengths and frame shapes change to what each app offers for an image start. The model already sees the subject, so keep the subject short and spend the words on the action and the camera move.