Generative AI for image creation

Currently, many digital artists use generative AI technology as a support to accelerate the delivery of their work. Nowadays it is possible to generate a corresponding image from a text sentence. There are several market solutions for this, including some available to be used through APIs. See some at this link: https://www.analyticsvidhya.com/blog/2023/08/ai-image-generators/.

I created a new application to use in IRIS taking advantage of one of these APIs. I chose the Imagine API. It allows up to 50 free calls per day, and has an interesting paid package that allows you to create thousands of images per month. To subscribe to the API and obtain an API key to use the service go to: https://platform.imagine.art/dashboard/auth.

Then you can use my application, changing your key, generate the JAR, copy it to the root of my IRIS project and then generate your images. My project is at https://github.com/yurimarx/imageaicreator.

The Image AI Creator in action

1. Copy, build and run the docker project:

git clone https://github.com/yurimarx/imageaicreator.git

$ docker-compose build
$ docker-compose up -d

2. Open http://localhost:/swagger-ui/index.html. On swagger explore put http://localhost:/image-ai-creator/_spec:

3. Run the method /generate passing in the body a text with instructions to generate the image (use english):

4. Download the png file on the link Download file and see the results:

5. See the image for the sentence "a ragdoll playing tennis" (the AI knows that ragdoll is type of cat, fantastic!):