Learning AI Video and Image Generation (My Beginner Journey)

Lately, I’ve been learning a few things from free resources on the internet—YouTube, Instagram, TikTok, you name it. I’m especially interested in AI video generation and image creation.

In this post, I want to share how I create videos using AI tools. I’m still learning, so if you have any suggestions or tips, feel free to let me know!

The first thing I usually do is go to ChatGPT and ask for a prompt to generate an image. The pictures I make are usually about a fat cat mimicking humans and working as a tour guide in Bali. I chose this theme because I’m quite familiar with the world of tour guiding. So, I ask ChatGPT to help me create a prompt for generating the cat character.

Next, I head over to Google’s ImageFX (you can search “Google Labs ImageFX” to find it) and paste the prompt from ChatGPT to design the character. I also use ChatGPT to create other prompts of the same cat doing different things—like sleeping, jumping, or falling.

Then, I animate these pictures using AI video tools. I usually use websites like wan.video, Digen AI, or Kling AI. These tools help bring the still images to life.

Finally, I go to CapCut to combine all the short clips and create one full video based on the story I had in mind.

In this story, the cat is watching a Rangda performance in a temple courtyard. He gets bored and falls asleep. In his dream, the monster Rangda grabs him! He suddenly jolts awake, falls from his chair, and everyone around starts laughing.

And here is the final result in video form! Hope you like it.

Watch the YouTube Short: