Artificial Intelligence applications seem infinite and depend on the creativity of their developers. But although it may seem paradoxical, one of the most recent uses seems to be substituting creative work, since through it illustrations and images are being generated that could be awarded to any artist.
Currently there are several artificial intelligences with the ability to generate works from a series of written instructions and in this publication we share some of the most popular platforms to generate this type of content
It is the most popular platform for generating images from text and has even been expanding its capabilities. It recently integrated the Outpainting tool, which aims to expand users’ creativity by continuing an image beyond its original borders by adding visual elements in the same artistic style, or by building a new narrative for works.
DALL-E is an AI capable of creating realistic images or paintings from a natural language description in text, where concepts, artistic styles or features can be combined.
Although a person provides a single description, the AI has the ability to create different variations of the same image and its operation is based on the fact that it has learned the relationship between the images and the text that describes them through a process called “diffusion”. ”.
The big problem with this platform is that to access it an invitation is required from the developer company, OpenAI, which is obtained through a waiting list.
This is that in addition to generating images from text, it has the ability to convert it into a long video, which makes a substantial difference compared to DALL-E.
It also has the ability to “extend” any image by integrating more elements without forgetting the original design and giving it exact continuity. Some of his examples are the iconic Windows landscape photo.
Google is one of the most innovative companies in terms of Artificial Intelligence and they could not be left out of this field. In this case, the company has , a tool that instead of creating new images, its objective is to collect data to strengthen the system.
Another of its purposes is to help avoid the bias of images that already exist on the internet and create more inclusive and diverse content, according to what the Mountain View company said.
where the user must type several words in certain fields so that illustrations are created immediately. Its use is free and it delivers a total of nine images that can be saved on the user’s device and shared on social networks.
This one is for people and you don’t need to provide any personal details to sign up. Its operation is also based on words, but the main difference is that the result can be customized by modifying the parameters of the image.
At this point the ability of the users comes in, because the more editing there is, the image becomes something unique, in addition to the quality (in pixels) also increasing. You can even choose a frame of the possible image to obtain a result that is closer to reality.
Artificial intelligences not only work to generate images from texts, but also to discover new styles. It is a platform that allows you to upload photographs of any person and after an hour of waiting it will generate different artistic styles, from a hyper-realistic work, a Renaissance or an anime drawing.