Ra-ta-ta
I put together this 50-seconds aficionado video using free tools like ConfyUI with generative models such as Flux for images and Hunyuan for video. I also used free versions of Suno, Luma, and CapCut for effects and editing.
Some static images come to life by the end of the video!
The funniest part? Suno, as always! I came up with these lyrics in 30 seconds, and let it do its magic:
Fiesta, yay! Fiesta now!
Live in colors, go!
Fiesta, yay! Fiesta now!
Love and friends, ra-ta-ta!
Loca, loco
Drums and coco
Live in colors
Love and friends, ra-ta-ta!
The images were also quickly generated using prompts like “Colourful happy people marching and dancing,” and similar.
A fun, fast experiment, amazing how generative AI keeps evolving! So many free tools to explore.
Experimenting with Unhappy People
I used my happy people to generate the video, but I also experimented with some sad, unhappy people… Won’t be making a video with them, but here are a few:
Unhappy People
[Insert images of unhappy people]
Conclusion
Generative AI is an exciting space to explore, and I’m excited to see how it continues to evolve. Who knows what kind of creative possibilities will arise from these tools?
FAQs
Q: What tools did you use to create this video?
A: I used ConfyUI, Flux, Hunyuan, Suno, Luma, and CapCut.
Q: How did you come up with the lyrics for the video?
A: I wrote them in 30 seconds using Suno’s AI-powered lyrics generator.
Q: What were the prompts you used for generating the images?
A: I used prompts like "Colourful happy people marching and dancing," and similar.
Q: Will you be making a video with the unhappy people?
A: No, I won’t be making a video with the unhappy people, but I’m including them here for your entertainment.
