Hello, Hive community. Today, I want to share with you a new passion that has sparked great curiosity and enthusiasm in me: creating images with artificial intelligence. Although I am completely new to this field, every day I spend exploring, I become more fascinated by the infinite possibilities this technology offers.
AI tools like MidJourney, DALL·E, and Stable Diffusion have completely changed the way digital art is created. What once took hours of skilled work can now be made in minutes with the right prompts. However, it’s not as simple as I thought at first. Creating the perfect prompt
"Sometimes I get epic photos, but with small or big problems that I’m not sure can be fixed, or if I should just discard the image because it’s not usable. The truth is, I don’t know how to fix those issues. Then I try 500 more times and never manage to get the same image again. Haha, I still have a lot to learn."
"Here are some examples of images I liked, but they have flaws."
This first image took quite a bit of effort to get it the way I wanted, but in the end, it had a flaw. I made a few more attempts, but none of them convinced me.
In the second image, I asked the AI to create a woman with a scaly body, dragon wings, and other details. After several failed attempts, I finally got it the way I wanted, although the version I liked has a lock of hair in her mouth. Haha!
In this image, I asked the AI to place a cannon on the arm, but instead, it ended up with a bunch of fingers. Haha! The good thing is that it didn’t take me much time to get the picture.
This was the first image I created, just a test to see if the AI could truly reflect everything I described. In this case, I asked for a dog on a bench with a bottle of rum, a lizard next to it, and other details. Everything appeared, but half of the dog ended up passing through the bench.
Here, I tried to create an image of Ronaldo and Messi. No matter how much I tried, I couldn’t get them to look very similar—honestly, I ended up with some cheap knockoffs, haha. But I’ll keep trying—I won’t give up!
*Here are some images that I believe turned out well and are my favorites so far.
*If you're interested in exploring AI-generated art, here are some platforms to get started:
MidJourney: You can access it via Discord. Visit https://www.midjourney.com and join their Discord server to start generating images.
DALL·E: Developed by OpenAI, it allows you to create stunning images from text descriptions. Try it at https://openai.com/dall-e.
Stable Diffusion: A powerful AI tool for image creation, available at https://stablediffusionweb.com.