

Open Source AI Filmmaking Tools - VFX AI With Analogue Footage, Anyone?
This year we watched a frontier AI model get switched off worldwide, in a matter of hours. Anyone who had built their production pipeline on it lost it by dinner.
That is one argument for going local. Here is the other.
Right now, hybrid AI filmmaking tools are asking you to upload faces, likenesses, and footage to their servers as a matter of course. Actors, talent, real people, with very little transparency about where that data goes or how it is used. For filmmakers, that is not just a privacy concern. It is a consent and rights issue that could come back to bite you, your clients, and the people in front of your camera.
The tool you can actually trust is the one that never leaves the room. Open weights, running on the machine in front of you. No subscription to cancel, no terms to change, no cloud to lock you out, no kill switch in someone else's hands, and no server receiving your talent's face without their knowledge.
So this month we run ComfyUI: the node-based, fully local way to run open source image and video models. Nothing uploaded. Nothing rented. Nothing that can be taken away.
And this month we suspend Rule 4. No subscription required.
🎬 What You'll Work On
"Why local and why now?" (20 min)
The honest version of what open source AI filmmaking can do on a laptop today, and what it still can't. We'll also get into the copyright and likeness question directly: why uploading footage and faces to cloud-based hybrid tools is a risk that filmmakers specifically need to understand, and what running locally actually protects you from.
The key technical point for this session: pulling a green key and dropping in a background is the easy half. The real test is the relight, making a subject actually sit in the light of its new scene, using only open source AI, on your own machine. That is the thing we're here to find out.
"Two teams. Green to final frame." (70 min)
Teams shoot a short greenscreen clip in the room. Gavin then runs a ComfyUI graph live that does two jobs: replace the background, and relight the subject so it belongs there. Open source models only. Nothing uploaded.
If you already have ComfyUI installed on your laptop, bring it and build alongside Gavin. If you don't, you're still fully in the session: you contribute by shooting the footage, directing the creative choices, and following the workflow step by step as Gavin runs it. The pipeline is transparent either way.
Multiple looks, compared at the end. Make it, break it, log it.
Debrief & Share
What worked, where it choked, where the relight held up and where it gave the subject away. What the local workflow protected that a cloud tool wouldn't have. And where the human stayed in charge.
⚔️ The Five Rules
Rule 1: Make, Not Talk — No endless AI theory. Build actual workflows in two hours that you can test Monday morning.
Rule 2: Teamwork = Human Open Source Bot — No passengers, no creative dictators. Everyone contributes, everyone rotates.
Rule 3: Don't Hoard Your Subscription Credits — Fast hours, API tokens, pro access — pool your compute power for the team. Generosity wins.
Rule 4: SUSPENDED THIS SESSION. No Subscription Required. This month we're going fully local. ComfyUI runs on Gavin's machine. Leave the Claude and Runway credits at home.
Rule 5: Leave Egos at the Door — Director, DP, editor, producer, fresh grad — everyone is equal at the table. Pure collaboration, pure learning.
⚠️ Important Notes
Bring a laptop with internet access. If you have ComfyUI already installed, bring it and you can build alongside Gavin during the session.
All experience levels welcome, but come ready to collaborate and experiment
In the event of oversubscription, Lorong AI members will be prioritized
🗣️ Facilitated by Gavin Lim (AI Film Lab)
Gavin Lim is founder of AI Film Lab, a Future of Work community exploring the intersection of AI technology and visual storytelling. A seasoned TV producer, director, and filmmaker with nearly thirty years of experience, Gavin leads practical exploration of AI tools that enhance rather than replace human creative judgment.
AI Film Lab has conducted AI filmmaking hackathons with Singapore media practitioners and led the first AI filmmaking hackathon at the Philippines' inaugural AI Festival (2025). Their approach centres on iteration over perfection and collaborative learning over isolated expertise.
More About the Series
FaiGHT CLUB is a monthly AI filmmaking lab bringing together professional filmmakers, creatives, and producers for hands-on exploration of AI tools that enhance rather than replace human craft. Each session tackles a specific production challenge through collaborative team sprints, guest case studies, and practical workflow development.
Tinker Time is Lorong AI's hands-on meetup combining guided workshops with open collaboration time for builders to share code, troubleshoot together, and experiment with AI development techniques.
Get involved: Learn more about Lorong AI | Speaker Sign-up | WhatsApp Community | LinkedIn | X