You’re not going to believe what I just found out about the new OpenAI Dalle model
OpenAI recently launched a beta program for their latest model Dalle 2.
“DALL·E 2 is a new AI system that can create realistic images and art from a description in natural language.”
I recently got access to the Dalle 2 model a few days ago and started playing around with it. It generates some pretty impressive quality pictures.
- “A bored ape riding a unicycle on the wing of an aeroplane”
Not too impressive right! Wait it gets better.
2. “A black banana with a purple orange fruit on a plate”
I tried confusing the AI a lil with my query “purple orange fruit” and succeeded 😅. I think….
It didn’t quite generate what I had in mind.
But then after doing some reading I refined my prompt style and it gave me better results.
“Jesus wearing a durag and diamond earrings with a nose piercing chilling next to the cross and sipping wine”
I was blown away by the level of detail it generated.
I tried pushing the model even more.
“planet with purple haze with floating trees, red comet leaving a fire trail in the sky and snow fairies floating around a pond, hyperrealistic,3d”
“the devil wearing gucci glasses, a leather jacket, golden loafers and a diamond briefcase walking towards me,3d render, hyperrealistic”
You can also upload images and have it generate variations of it.
That brings me to the end of this post. There is another model which I am currently testing out called Mid-Journey. I will be writing about it soon.
Please clap and follow for more content like this.