🧰 UtlKit

AI Video Prompt Generator

Pick a mode and model, describe your subject, then tap the cards to add shot, camera, lighting, and style details. Your prompt builds live and copies in one click.

Prompt language: English

Prompt preview

Describe your subject or tap the cards above to start building your prompt.

🐛

Report a Problem

Found a bug or have a suggestion? Help us improve this tool.

📊 Data Summary (auto-filled)

Tool: video-prompt-generator · /tools/video-prompt-generator/

mode: t2v

model: Kling

language: en

selected: [object Object]

What is this tool?

The AI Video Prompt Generator builds structured prompts for text-to-video and image-to-video AI models. You describe your subject, then tap image cards across shot size, camera movement, angle, lighting, style, and more to stack details. It supports models like Kling, Sora, Veo, and Runway, appends a per-model quality suffix, and lets you copy the result as text or JSON, all in your browser.

When to use this tool

  • Prompt Chinese models in Chinese

    Select Kling, Seedance, or another Chinese model on the Chinese page and get a ready-to-paste prompt written in Chinese, including shot and camera terminology the model expects.

  • Build layered prompts for Western models

    Stack shot size, movement, lighting, and style cards to produce a layered English prompt for Sora, Veo, Runway, Luma, or Pika that covers every axis the model supports.

  • Learn cinematography vocabulary

    Each card pairs a named technique with a reference image, so you can explore shot sizes, camera angles, and lighting setups while building a prompt and reuse the terminology in your own descriptions.

How to use

  1. 1

    Choose generation mode and model

    Pick Text → Video or Image → Video and select your target model from Kling, Sora, Veo, and more.

  2. 2

    Describe your subject

    Enter your subject and scene in text-to-video mode, or motion and camera notes in image-to-video mode.

  3. 3

    Add visual details

    Tap the image cards across shot size, camera movement, angle, lighting, and style to stack details into your prompt.

  4. 4

    Copy the prompt

    Preview the prompt live, then copy it as plain text or as JSON with the full option list.

Frequently Asked Questions

What is the difference between text-to-video and image-to-video mode?

In text-to-video mode the model generates the whole scene from your text, so you control subject, framing, camera, and lighting. In image-to-video mode the first frame comes from an image you will provide in the video tool, so this generator focuses on motion and camera. The shot size, angle, and composition categories are hidden because your image already defines them.

Which video models are supported?

Ten models are covered: Kling, Seedance, Hailuo, Wan 2.2, and Vidu from Chinese providers, plus Sora 2, Veo 3, Runway Gen-4, Luma Dream Machine, and Pika 2.2. Selecting a model appends a quality suffix tuned to that model at the end of your prompt.

What language will my prompt be in?

For the Chinese models (Kling, Seedance, Hailuo, Wan, Vidu), the prompt is generated in Chinese when you use this tool on the Chinese-language page, since those models respond best to Chinese prompts. For all other models, the prompt is in English. You can always switch page language or rewrite the subject in your preferred language.

Is my data uploaded to a server?

No. The entire tool runs in your browser: the prompt is assembled locally from your text and the options you pick, and nothing is sent to any server. The reference images are static files served with the page, and your subject text stays on your device.

Related tools