Cafe by Mark DK Berry (Music Video)

Cafe by Mark DK Berry

*(No AI was used in making the music; only for the video footage. All of the footage is generated using free AI)*

This moment marks when AI put storytelling back into people's hands. I made this music video after the release of the first working, free text-to-video AI model on ComfyUI on Dec 5, 2024. It cost only my time, computer, and electricity.

*Time Taken:*

It took 4 days, including learning new tools. I avoided the 3-month rabbit hole I fell into making “Fallen Angel” using Unreal Engine and Metahumans. This time, I stuck to a strict timeline of 5 days. Rendering 2 seconds (max my PC could do) of 512x416 video at 24 fps took 5–8 minutes per render. Many prompts no tweaking would fix—so I kept to strict time limits to get it done in 5 days.

Day 1 was for main content, Day 2 for fixing ideas, Day 3 for tidying in DaVinci, and Day 4 for final edits and color grading (likely overdone—sorry, colorists).

*Equipment & Tools:*

Software: ComfyUI AI (portable, free) with Hunyuan text-to-video models (GGUF for better results), DaVinci Resolve (free version), and FFmpeg for slowing clips and smoothing interpolation.

Hardware: A Windows 10 PC with an RTX 3060 (12GB VRAM). 512x416 resolution balanced quality with my PC's capabilities. Bigger sizes caused issues, and smaller ones lost clarity.

Prompts worked best when kept simple, e.g., *“hot female model in a red pencil dress walking away at an old English train station, realistic and cinematic, daytime.”*

*Current Challenges:*

AI generated max 2 seconds per prompt on my PC else it fell over, and prompts hit character limits around 350. While the results were clear, stretching 2 seconds to 8 via FFmpeg which worked to buy time, but added blur and distortion.

AI couldn’t consistently generate the same face or dress style, and aerial shots with women proved tricky. Ideas like morphing characters, cartoon seque ideas, or greenscreen effects often led to cheesy results, so I scrapped most of them. Despite these constraints, Hunyuan delivered fantastic results, even without advanced tools like ControlNet (still early days).

The journey has just begun, and this opens doors for more videos as the tech evolves. Hollywood is on notice, we can now make our own movies for free. This is where it all begins!

*Follow Me:*

markdkberry.com
markdkberry.bandcamp.com
IG: @markdkberry
YT: @markdkberry
Full music video back catalog: https://rumble.com/c/c-1331684

#hunyuan #ai #musicvideo #markdkberry #comfyui #opensource #freeai