๐For the last 2 months, I've been heads-down exploring ai image & video generation as my new personal project. I was shock by the capabilities of current ai image/video space. But every ai creators face a common pain point.. this sh*t is hard. Haha. Thats why all youre seeing are ai slops.
Then about 1 month ago, I sent the kids to my relative for few weeks and lock myself in a room and went nerd out to build a tool that lets me take an idea and turn it into a profession cinematic video. I recorded it working on a real project and wanted to share what it actually does โ and why I'm pouring everything into it.
The idea in a nutshell: Instead of guessing what makes a video great, my tool studies one:
โ I give it an original video as a study case (here's the one I used: [youtube]) โ It analyzes that video and pulls out its DNA โ the small details in every component that make it work: the shots, the pacing, the sound, the transitions, the feel. โ Then it reverse-engineers that DNA into something completely new and my own โ and carries it all the way through, even into the editing, mostly automatically. The Unfolded short film bellow received the same DNA treatment, as you will see, the context is similar ..however, it produced a very unique animation perspective using origami. Every user who analyzes a film makes the library richer for the next one. That's a network effect โ the rare thing that actually compounds. GitHub for film DNA: fork a look, make it yours, push it back.
I have tried to use it to branch off ideas from Game of Thrones series. It is very complex to keep track of all the different kingdoms, characters, props, and story development. But i think i got it figured out.
Theres no one size fit all approach for different type of contents. Horror dna cant get mix up with cartoon ๐. But this is the closest thing to a โreusableโ end to end video generation. Correct me if im wrong but there isnt a product out there that can solve this yet. This is a foundation to a full content creation pipeline - you re using a proven video as a reference for your own video. Once you figured out your winning format, automate it to create video daily/weekly is the easy part.
Imagine this can be apply to real estate, cinematic movie, music video, reconstruct video, demo video, etc..
What the system can do today:
- ๐ฌ Analyze a reference video and extract its DNA + Build world assets
- ๐ฌ Turn that into a fresh shot list and generate the clips
- ๐ Build the sound design + multitrack mix right in the app
- โ๏ธ Edit and render the final cut โ one click to MP4
- โป๏ธ Keep everything as reusable building blocks for the next project
- It's not perfect yet โ there's still real work to do and I'm fine-tuning it every single day. But it already takes me from "a video I admire" to "a finished video of my own" faster than I ever could by hand.
Why I'm doing this: I'm a single dad of two boys (9 and 5), working 15+ hour days, and this is my passion โ honestly something all three of us are into together. AI video and Vibe code clicked for me about two months ago and I haven't stopped since. I'm not a super technical person but passion is my strength, I believe this is the future.
Big thanks to Coach โ a lot of how I've structured this comes straight from the ICM approach you teach. Happy to go deeper on any piece, and always open to use-case ideas. I would love to also help make any ad to promote the group and upcoming app๐ Now, grill me ! =] ๐๏ธP.s: If youโre interested in contributing or testing in the near future, pls leave me a comment bellow so my agent can keep track of this post. Tell me how is this workflow relate to your current project or skillset