Michael Siarkowski

Generative AI Production

• Produced two feature documentaries built on substantial AI-generated footage. The first drew 100K+ YouTube views in its first week (~120K to date); the second, completed 2026, is in distribution negotiations (not yet released).
• Compressed production cycles from 6–12 months with a full crew to about 4 weeks with one person, at ~$3K in AI generation spend per production (generation costs only) — replacing crew, location, and wardrobe shoots with AI generation.
• Designed, coded, and shipped mico (Tauri + React; Claude/LLM, image-generation, and video-generation APIs): one tool unifying concept, script, AI previsualization, storyboarding, reference art, and shot generation — cut pre-production from 2 weeks to under 1; used in production by the studio team.
• Generative AI in production since 2022: Stable Diffusion (WebUI, then ComfyUI; trained custom LoRAs), GPT-SoVITS voice cloning, local LLMs via Ollama, Claude and GPT; standardized on Seedance for video generation after evaluating Veo and Kling in production.

Real-Time 3D / VFX

• Own the studio’s entire 3D pipeline as its sole 3D artist — modeling, look-dev, environments, rigging, animation, motion capture, FX, rendering, compositing — across Unreal Engine 5, Houdini, Nuke, Blender, ZBrush, Marvelous Designer.
• Build real-time cinematics in UE5 — Sequencer, Blueprint, Niagara FX, MetaHuman, Chaos cloth and physics, Lumen/Nanite — for documentary and commercial productions.
• Promoted to department lead in 2025; hired and mentored a second VFX artist; shipped 80+ videos and 5 major productions.

Studio Engineering

• Designed and built two 5-camera recording stages end-to-end — cameras, lighting, audio, encoding workstations, streaming infrastructure — and have run real-time UE5 on-stage graphics using virtual-production workflows.

• Edited event and promotional videos for local clients; designed and installed livestream setups.