Today I messed around with some AI stuff, and I want to share what I did. It was kinda fun, I guess.
So, I started by getting this model. This AI model named InternVL2-2B. I heard about it from some people on Twitter talking about something called “2B” and saying it’s all you need, whatever that means. And the image quality is awesome. So, I thought, why not give it a try?
First, I grabbed the code from the internet. Then, I had to install a bunch of stuff to make it work on my computer. It was a bit of a pain, but I got it done after some trial and error. It took me quite a while, actually. Oh man, it’s really a long time.
After everything was set up, I started playing around with the model. I tried feeding it some images and text, just to see what it could do. It was pretty cool to see how it could understand and generate stuff based on what I gave it.
Then I try to reprint my 2B statue, but the result is not what I expected. But the AI can generate images based on my text, it’s a good feature.
- First step, find the code.
- Second step, install all dependencies.
- Third step, test the model.
- Last step, try to reprint my 2B model, and find a good feature.
I also tried using it to create some short videos. There’s this thing called CogVideo, and they recently updated their model. I thought it would be fun to try generating some videos based on my ideas, but I didn’t get very far with that yet. I will try it later.
My Feeling
Overall, it was an interesting experience. I learned a bit about how these AI models work, and it’s pretty amazing what they can do. Still, it’s not perfect, and there’s a lot of room for improvement. But for a casual user like me, it’s definitely something worth checking out.
Anyway, that’s my little AI adventure for today. Maybe I’ll try something else tomorrow. Who knows?
