TC Ensina: how to generate images using Gemini, an artificial intelligence (AI) from Google

Google launches Gemini (antigo Bard) to directly compete with big shores like ChatGPT and Bing, and assim like our counterpartsartificial intelligence is also capable of producing images!

Today, then a sequence in our square of sentences and tutorialsentrust yourself to the following image creation with the text command attracted by Gemini and use your imagination!

Very similar in form to what is seen in other AIs, like DALL-E and Midjourney, Gemini also allows our users to create images using text commands. So, I invite you to request an image following a description and to save the result.

Attention! After this tutorial, the commands for generating images accurately will – necessarily – be in English (or another supported language). No, it is proven that it is a passage, and that the recurso is launched. In the coming months, full support for português must be included.

In what form, if you do not control the English languageyou can use Google Translator (or até mesmo outras IA) to help you translate your prompt. Then I'm colar a description traduzida no Gemini e mandarin ver!

Confirm how to complete the process with the detailed logo by following:

• First access to Gemini on your browser Click here You have access to www.gemini.google.com;
• Now insert the description of the image you want to generate.

  • For example, “create a photo of a cat jumping to catch a ball” – translation from Portuguese: “shout a photo of a cat pulando pour pegar uma bola”;
  • If you like, here is a picture for reference.

• Keep the process;
• If you are not satisfied with the results, click “Read more“To receive more alternatives or modify the generated images – the AI ​​is able to hear the context.

For example, AI will generate 4 different images for the same commander. Click on the images for your ampliadas. Click on the set icon located in the song directly from the image to get the full resolution.

Check the images sent with our prompt:

Google Gemini uses SynthID to insert a water mark and indicate that the image was created by artificial intelligence. So even though I can't see a mark on my old man, It is possible to check the origin of the image use the appropriate software.

It is valid to say that, currently, As Gemini images cannot be used for commercial purposes. As images can be used for educational or fishing purposes, or for estritamente people.

Additionally, the AI ​​model that will be used to create an image knows how to discover what might be a difference for better results. Therefore, consider these points for writing your prompts:

• Seja (but) specific: Includes details on cores, objects, storyline, style and even lighting. Avoid vague or generic descriptions.
• Seja succinto: Long, highly complex sentences may be more difficult for AI to interpret. Therefore, express your idea clearly and directly;
• Experience : If you are not satisfied with the first results, experiment with the varied descriptions and get new images. Persiga o resultado que deseja;
• Market references: These are examples of what you are looking for. You can do this by adding an image or by colando or a link to a desired image;
• Explore AI documentation to learn more about your remedies.

After this and other AI efforts provide satisfactory results for image generation, they are not capable of replacing the creativity and sensitivity of our human beings. Artistic expression is now a unique expression of humanity. Therefore, Although it is possible and necessary, opt for a meat and bones artist.