ChatGBot
ModelsFeaturesApp BuilderPricingFAQ
Sign inStart free
  1. Learn Center
  2. Images and video
  3. Make a short video from a prompt

Make a short video from a prompt

Describe one scene, pick a video model and a 16:9 or 9:16 shape, and turn your idea into a short clip.

Updated Nov 18, 2026 · 3 min read

Video turns a written idea into a short clip. You describe a scene, choose a video model and the shape of the clip, and ChatGBot makes the video for you. Models marked Pro need a Pro subscription.

It helps when you want a quick visual for social media, a moving background for a presentation, a mood clip for an idea, or just a fun way to bring a picture in your head to life. You don't need a camera, actors or editing skills. A clear description of one scene is enough.

Step by step

  1. Click Video in the sidebar.
  2. Pick a video model from the model menu.
  3. Choose the shape of the clip: 16:9 for wide screens, or 9:16 for phones, Reels and Stories.
  4. Describe one scene: who or what is in it, what moves, where it happens and how the camera moves.
  5. Send your prompt and wait for the clip.
  6. Watch the result. If it isn't quite right, change your description and try again.

Example prompts

  • "A paper boat floats down a rainy city street, camera follows from above, soft evening light."
  • "A cup of coffee on a wooden table, steam rising slowly, warm morning sun through a window."
  • "A golden retriever runs across a beach at sunset, slow motion, camera tracks alongside."
  • "Neon signs flicker on a quiet street at night, light rain, camera slowly moves forward."
  • "Colourful autumn leaves fall in a park, gentle wind, calm and peaceful mood."

Tips

  • Keep it to one scene. One clear action works better than a story with several steps.
  • Describe movement. Say what moves and how: "slowly", "spins", "flows", "walks towards the camera".
  • Direct the camera. Words such as "close-up", "wide shot", "camera follows" or "slow zoom in" shape the clip.
  • Name the light and mood. Try "golden hour", "neon night", "soft morning fog" or "bright and cheerful".
  • Pick the shape first. Think about where you'll post the clip, and choose 16:9 or 9:16 to match.
  • Change one thing at a time. When you try again, adjust only one detail so you can see what helped.
  • Think like a director. Write your prompt like a short film direction: subject, action, place, light, then camera.
  • Save what works. Keep prompts that work well, so you can reuse them for a series of clips in the same style.

Common questions

Which aspect ratio should I choose?

Choose 16:9 for YouTube, presentations and wide screens. Choose 9:16 for vertical phone videos such as Reels, Shorts and Stories.

Do I need Pro to make videos?

Models marked Pro in the model menu need a Pro subscription. If you pick one on the Free plan, you'll be asked to upgrade.

Why doesn't my clip match my whole story?

Clips are short, so they work best with one scene and one main action. Split a longer idea into several prompts and make one clip for each part.

Can I start from an image idea?

Yes. A good image prompt is a good start for a video prompt. Add what moves and how the camera moves.

Related guides

  • Make a vertical video
  • Create an image from a description
  • Write better image prompts

On this page

  • Step by step
  • Example prompts
  • Tips
  • Common questions
  • Related guides
ChatGBot

One subscription for every leading AI model: chat, images, web search, documents, Canvas and the App Builder.

support@chatgbot.ai

Product

ModelsFeaturesApp BuilderPricingFAQSign in

Legal

Terms of UsePrivacy PolicyRefund Policy
BlogGemini 4 Neon: Google's New Mid-Tier Model, ExplainedGPT-6.2 Sol: OpenAI's Everyday Model Gets Better at the Same PriceGPT-6.2 Astra: OpenAI's Flagship Gets Cheaper and SmarterQwen4-Max: Alibaba's New Flagship Model, ExplainedAll articles

© 2026 ChatGBot. Operated by 42 Dijital Yazılım Limited Şirketi.

Chatgbot is an independent AI interface. It is not affiliated with, endorsed by, or sponsored by OpenAI, Anthropic, Google, xAI, DeepSeek, Qwen, GLM, or other model providers. Model names and trademarks belong to their respective owners. Model availability may vary by plan, region, and provider access.