{"id":13209,"date":"2023-10-20T08:57:16","date_gmt":"2023-10-20T06:57:16","guid":{"rendered":"https:\/\/ddigitals.net\/?p=13209"},"modified":"2024-09-13T17:37:17","modified_gmt":"2024-09-13T15:37:17","slug":"ia-to-create-images","status":"publish","type":"post","link":"https:\/\/ddigitals.net\/en\/blog\/digital-marketing\/ia-to-create-images\/","title":{"rendered":"How to use AI to create images?"},"content":{"rendered":"

The AI to create images <\/strong>has become an indispensable tool for content creators. The possibility to create tailor-made images<\/strong>without having to rely on the stock<\/em> The use of image banks (or sometimes limited free image banks) has been a revolution.<\/p>\n\n\n\n

Of course, not everything is rosy. At the same time as there are more and more AI tools to create images<\/strong>But there are also plenty of detractors. In the United States alone, there are more than a hundred artist's claims to artificial intelligence tools<\/a>.<\/p>\n\n\n\n

The argument is simple. As the IA<\/strong> need copyrighted images<\/strong> to train, the resulting images would be straightforwardly a plagiarism<\/strong>.<\/p>\n\n\n\n

Surely we have seen on social networks trends such as turning certain images into a P\u00edxar film poster<\/strong> or Disney<\/strong>. For the original authors of these posters, artificial intelligence is plagiarising them, using their work without paying for image rights.<\/strong><\/p>\n\n\n\n

With many of these payment instruments<\/strong> and being used for commercial purposes, the authors argue that it is causing them direct economic harm.<\/p>\n\n\n\n

However, the speed of the judicial system is lagging far behind the rapid evolution of this type of tool. We find, therefore, a three-speed scenario.<\/p>\n\n\n\n

On the one hand, the tools are evolving faster and faster<\/strong>The one hand, in the generation of images, as well as in the generation of text or programming. On the other hand, the legislative framework<\/strong> has not yet been developed, although the first drafts are beginning to emerge.<\/p>\n\n\n\n

Finally, the court proceedings<\/strong> are even slower. Meanwhile, users are still learning how to get the most out of it. And that's what we'll try to unpack in this article.<\/p>\n\n\n\n

The limitations of artificial intelligence in image generation<\/h2>\n\n\n\n
\"Photoshop<\/figure>\n\n\n\n

The first thing we have to take into account in order to using AI to create images<\/strong>is that it is still a technology in development<\/strong>. This means that it will probably sound better in our heads and we may be disenchanted with the first results.<\/p>\n\n\n\n

This friction is normal in a user's first interactions with artificial intelligences. We think that they can do everything and the reality is that, on the one hand, giving them precise instructions is not such an easy task and, on the other hand, depending on the tool, they will be more or less capable.<\/p>\n\n\n\n

Depending on the tool we use, we will discover that each has its weaknesses<\/strong>. Some don't get the eyes right, others fail in the hands, in the backgrounds, etc. Nowadays, although there are options such as Midjourney<\/a><\/strong> which give quite good results, are still far from achieving, quickly, the result we are looking for.<\/p>\n\n\n\n

Others, such as the Canva's artificial intelligence<\/strong>is not even capable of understand a negative prompt<\/strong>. That is, if we tell it that we don't want something to appear in the image, it will understand that we do. And, in addition, we will not be able to modify the images already generated, but it will create new ones from scratch.<\/p>\n\n\n\n

Indeed, this is one of the arguments of artists using artificial intelligence tools. In some media cases, they have confirmed that they have had to introduce more than 500 prompts<\/em> (instructions) to achieve the result.<\/p>\n\n\n\n

This process of introducing prompts becomes the new artistic process.<\/p>\n\n\n\n

As content creators, if we want to speed up the search for images<\/strong>If we do, we probably don't have time to keep introducing 500 variations on the original image.<\/p>\n\n\n\n