Q: Как мога да създавам по-добри изображения?

Start with a simple formula. Try <Create/generate an image of> <subject> <action> <scene> and then build from there. For example, "Create an image of a cat napping in a sunbeam on a windowsill." Be specific with as much detail as you can dream. Prompts should include as many specifics as you can think of, so instead of saying, "Create an image of a woman in a red dress," try "Create an image of a young woman in a red dress running through a park." The more details you provide, the better Gemini is at following your instructions. Take composition, style, and image quality into consideration. Think about how you want the elements in your image to be arranged (composition), the visual style you want to achieve (style), the desired level of image quality (image quality), and the aspect ratio (size). Try something like, “Generate an image of a blurry poky porcupine flying in space in the style of an oil painting with 2:3 aspect ratio.” Creativity is your friend. Gemini is great at creating surreal objects and unique scenes. Let your imagination run wild. If you don’t like what you see, just ask Gemini to change it. With our image editing model you can take control of your images by telling Gemini to change the background, replace an object, or add an element – all while preserving the details you love.

Question 1

Генерирането на изображения налице ли е в държавата ми?

Accepted Answer

Генерирането на изображения с AI е налице на всички езици и във всички държави, където се предлага приложението Gemini.

Question 2

How can I find the image generation and editing model?

Accepted Answer

To access Nano Banana, select ”🍌Create images” from the tools menu and “Fast” from the model menu. Then add a prompt or upload an image to edit.
To access Nano Banana Pro, select ”🍌Create images” from the tools menu and “Thinking” from the model menu. Then add a prompt or upload an image to edit.

Note: Once you hit your limit using Nano Banana Pro, you will automatically default to using Nano Banana image model until you reach that limit.

Question 3

Как мога да създавам по-добри изображения?

Accepted Answer

Start with a simple formula. Try and then build from there. For example, "Create an image of a cat napping in a sunbeam on a windowsill." Be specific with as much detail as you can dream. Prompts should include as many specifics as you can think of, so instead of saying, "Create an image of a woman in a red dress," try "Create an image of a young woman in a red dress running through a park." The more details you provide, the better Gemini is at following your instructions. Take composition, style, and image quality into consideration. Think about how you want the elements in your image to be arranged (composition), the visual style you want to achieve (style), the desired level of image quality (image quality), and the aspect ratio (size). Try something like, “Generate an image of a blurry poky porcupine flying in space in the style of an oil painting with 2:3 aspect ratio.” Creativity is your friend. Gemini is great at creating surreal objects and unique scenes. Let your imagination run wild. If you don’t like what you see, just ask Gemini to change it. With our image editing model you can take control of your images by telling Gemini to change the background, replace an object, or add an element – all while preserving the details you love.

Question 4

Какъв е подходът на Gemini към безопасността?

Accepted Answer

В съответствие с принципите ни за AI този генератор на изображения с AI е проектиран с отговорен подход. За да се гарантира, че има ясно разграничение между визуалните елементи, създадени с Gemini, и оригиналните човешки произведения на изкуството, Gemini използва невидим воден знак SynthID, както и видим воден знак, за да показва, че са генерирани от AI.

Изходните резултати на Gemini се определят предимно от подканите на потребителите. Като всеки инструмент с генеративен AI може да има отделни случаи, когато се създава съдържание, което според някои е неприемливо. Ще продължим да се вслушваме в отзивите ви, изпратени чрез бутона „Харесва ми“/„Не ми харесва“, и да правим текущи подобрения. За да научите повече подробности, можете да прочетете за подхода ни на нашия уебсайт.

Question 5

How can I tell if an image was created with Google AI?

Accepted Answer

Simply upload an image to the Gemini app and ask if it was generated by Google AI. This verification is powered by SynthID, our digital watermarking technology. It is currently available for images, with audio and video support coming soon.

You can find out more about how we’re increasing transparency in AI content with SynthID in our blog post.