Skip to main content

Return to Comfyui Workflows (also accessible via "Workshop" in the menu bar)

"CAFE"

"Cafe" AI music video by Mark DK Berry.

WORKFLOWS & PROJECT DETAILS

🎥 Description

A woman walking through life, finds the solution to fix what she cannot. She isn't the first to figure it out.


🎬 About the Project

This was the first AI Video I did with Comfyui, and so the other workflows are probably better as they improved over time. The Hunyuan text-to-video model had been out since 5th Dec 2024, so I found enough info to help me get going with it. I then set myself a limit of 5 days to see what I could create. I had spent 3 months working on "Fallen Angel" in UE5 and the result had been disappointing, so was aware of the need for restricting myself going in. If it worked out, I could always do another. It worked out.


⚠️ Key Challenges

AI generated max 2 seconds per prompt on my PC else it fell over, and prompts hit character limits around 350 tokens with that Hunyuan t2v model and didn't obey the requests very easily. While the results were clear, stretching 2 seconds into 8 using FFmpeg worked to buy time, but added blur and distortion.

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


🔧 Workflows & Tools Used


⏱️ Time & Energy Investment

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


💻 Hardware

All of it was done on a regular home PC.


🧰 Software Stack


🎨 Loras Used & Trained

N/A


📺 Resolution & Rendering Details

512 x 416 resolution balanced quality with the model and my PC's capabilities at that time. Bigger sizes caused issues, and smaller ones lost clarity.


😵‍💫 Final Thoughts

As a first attempt I was blown away by what was possible. It had lots of issues, but I knew it was headed somewhere incredible, and I had jumped in right on time - nice and early.


back to top

Related Content

Narrated Films

Collection of ComfyUI workflows for AI narrated film creation, including detailed explanations and...

workflows ai-videos comfyui

Sirena music video

AI music video 'Sirena' by Mark DK Berry - underwater romance concept with detailed workflows and...

workflows ai-videos music-videos

The Name Of The Game Is Power

AI music video 'The Name Of The Game Is Power' by Mark DK Berry - Bond-style theme with Wan 2.1...

workflows ai-videos music-videos

I've Got All That You Need

AI music video 'I've Got All That You Need' by Mark DK Berry - workflows and project details for...

workflows ai-videos music-videos

I'm Still Alive (In The Naked Disco Of My Mind)

AI music video 'I'm Still Alive (In The Naked Disco Of My Mind)' by Mark DK Berry - film montage...

workflows ai-videos music-videos

Baes With Guns

AI music video 'Baes With Guns' by Mark DK Berry - workflows and project details for ComfyUI...

workflows ai-videos music-videos

Kali

AI music video 'Kali' by Mark DK Berry - workflows and project details for ComfyUI implementation...

workflows ai-videos music-videos

Footprints In Eternity

Narrated noir AI video 'Footprints In Eternity' by Mark DK Berry - detailed workflows and project...

workflows ai-videos comfyui

Next Project

Future AI video projects by Mark DK Berry - research, development, and upcoming workflow...

workflows ai-videos

Research & Development

AI video research and development by Mark DK Berry - latest techniques, workflows, and discoveries...

workflows ai-videos comfyui

Music Videos

Collection of ComfyUI workflows for AI music video creation, including detailed explanations and...

workflows ai-videos music-videos

We use cookies to improve your experience on our website. By continuing to browse, you consent to our use of cookies. Learn more