Filmmaker and creative technologist exploring AI, Unreal Engine, and more.

Minneapolis, MN
TALES OF GRIMWICKE — Chapter I is 22 minutes of AI fantasy animation inspired by the many anthropomorphic animal stories I read as a kid, with a dark twist: The model: Seedance 2.5 (@ByteDanceSeed_ ) via @Segmind_ai. 847 takes generated, mostly 30-second multi-shot prompts, over 5 hours of footage. 127 clips made the cut. About $4.5k in generation, four weeks from first take to publish. Characters and locations came out of @midjourney. Using MJ for the location plates was a revelation: the cinematography and art direction are a level above, and it renders far better as a plate than Nano Banana or GPT Image. Nano Banana (@GoogleDeepMind run on @fal) did the heavy lifting editing those plates, building anchor frames and turning MJ characters into turnaround sheets. Then I let Seedance do as much of the framing and camera operating as possible. That gave the best results. A lot of what I do in my Unreal Engine films came with me: a handheld, imperfect camera operator instead of smooth moves, focus hunting, and above all weather and atmospherics. The model does water, snow, smoke and rain really well, and leaning into that is what keeps it from looking like a Temu Pixar film. The tools I built: a portal (Node on @flydotio) that holds the bible, the refs, every prompt and every take, with a Claude agent (@claudeai) that writes the prompts to the house rules. A Premiere Pro (@AdobeVideo) panel that browses the archive, drops selects on the timeline, versions the project, strips music, and sends fixes back to Seedance. Everything is done in 720p with no upscaling, because it looks terrible. Narration is my own voice through @ElevenLabs speech-to-speech. Music from @Artlist_io. None of this would exist without @PJaccetturo and @Kavanthekid. Their narrative work, Nexus and Chronicles of Bone, proved long-form AI film was possible, and their podcasts, newsletters and X posts, updated constantly as the workflow changes under everyone's feet, showed how to actually do it. Chapter II is currently in the works and I will release it initially on my YouTube channel, The Darkest Age (@CharlieDriscollAI). Consider subscribing there to see it as soon as it drops!
536
651
5,942
1,252,336
What if Leonardo da Vinci's deadliest war machines had actually been built? I spent ~$3,000 and built my own AI pipeline to find out. A 3:45 concept trailer for a show you could watch on HBO, made entirely with Seedance 2.0. Inspired by the work of @PJaccetturo and @Kavanthekid who have put out some incredible films and content on their process. I used Claude Code to build my own proprietary Gen-AI platform, pulling image gen API's with @fal and a Seedance 2.0 gens from @Segmind_ai (cheapest API I could find, and most relaxed around the realistic faces censorship) to a @flydotio server, and even made my own Adobe Premiere plugin to stream my generations directly to my editing bin for lowest friction possible. Using a remote control session with Claude, I could chat entire scenes into existence while on the go, since I had essentially created my own filmmaking agent who knew the project inside and out. More details below!
Made with AI
6
6
108
4,894
I committed what I believe to be the cardinal sin of AI filmmaking. I dove straight into generating visuals without really planning my emotional beats, character arcs, or trailer structure first. Writing is still the most important part, especially now that the spectacle and scale and visuals come so easily. I am definitely looking to collaborate with any writers who would like to develop IP, short films, and commercials.
1
3
171
This started as a Seedance experiment and became a 3:45 trailer for something I actually believe in. HBO, I'm ready. Happy to answer anything about the process below.
2
147