Text to images and videos, Gemini’s new surprise
Text to images and videos, Gemini's new surprise
In terms of artificial intelligence, Google’s chatbot Gemini is no longer just a question-answering machine. It is gradually becoming a modern creative tool through which users can easily create images and videos from text.
With Gemini, it is possible to turn imaginary scenes into reality in just a few seconds. All that is needed is correct and clear instructions or prompts. Let’s see how to create images and videos using Gemini.
How to create an image
- First, enter the Gemini website or mobile app.
- Write a detailed description of the type of image you want.
Example: ‘A cat in a blue spacesuit floating in space.’
Remember, the more clearly you specify the lighting, color, style (such as cinematic or oil painting), the better the result will be.
- Press Enter. In a moment, Gemini will show multiple images or variations.
- If you want to change any part of the image, give new instructions.
For example: ‘Add a red hat to the cat’s head.’
How to create a video
Google is currently integrating its video creation tool Veo with Gemini, allowing users to create short video clips or cinematic scenes.
Write a prompt:
Write down clearly what you want to see in the video.
Example: ‘A drone shot moving over a mountain as the sun rises.’
Decide on a style:
Will the video be slow-motion or fast-motion? Which way will the camera turn? What will the weather be like? Providing this information will make the video more realistic and professional.
If you don’t like the first video you create, you can change the camera angle, speed, or environment with new instructions.
