AI Character & Shot Production Pipelines
Reference-driven AI workflows that keep characters and environments consistent across shots, from brief to edit-ready stills and video.
work.sergioazevedo.pt/projects/ai-creative-production-systems
Sérgio Azevedo
Creative Technologist
Professional Summary
Creative Technologist with 10+ years leading distributed creative teams and building AI-assisted production systems for remote product companies. Led a remote team of 5 while cutting asset turnaround 25% and accelerating production cycles 40% through standardized, reusable pipelines. Combines hands-on craft in video, motion, 3D/XR, and brand systems with the process discipline to scale creative output without losing quality.
Core Skills
Professional Experience
Glimpse Learning
Remote, New York, USA
11/2025 – Present
Creative Technologist
The Glimpse Group
Remote, New York, USA
11/2022 – 07/2026
Creative Technologist / Senior 3D Artist
inciteVR
Remote, Porto, Portugal
09/2020 – 12/2022
Co-founder · Senior 3D Artist / Art Director
Adtalem Global Education
Remote, Chicago, USA
08/2015 – 07/2020
3D Game Artist
beActive Media
Vila do Conde, Portugal
01/2012 – 07/2015
3D Designer / Motion Graphics Artist
Selected Systems & Portfolio
AI Workflow Systems
Glimpse Group
AI Creative Production Systems — Character, Environment & Shot Pipelines
Standard AI generation breaks character and environment consistency across sessions — built a reference architecture that pins visual rules so any generation step produces on-system results. Reduced shot production cycle from brief to ready-for-edit across 3+ campaigns. Reusable reference pack held visual consistency across 20+ characters and 4 environment systems.
AI Video Production
Fictional brand
Rootwell — A 13-Shot AI Video Ad, Brief to Final Cut
One character, wardrobe, room and product held across all 13 shots. Every shot was drafted at least twice at 480p and only the chosen take was finalized at 1080p: 1,088 credits against about 1,970 for three full-resolution takes per shot, roughly 45% less. Ten of the 13 shots were approved from their first pair of drafts; the other three were fixed in the prompt, not re-rolled.
3D-to-Video Automation System
Ev2MK
Render-to-Video Pipeline — 3D Asset Automation + Scalable Motion System
Reduced repetitive manual production work by systemizing the full path from 3D render to final video. What previously required a full day of manual work per asset now runs as a repeatable, data-driven pipeline capable of generating large volumes of consistent animated content while preserving creative control over characters, visuals, motion, audio direction, and final composition.
Brand Design System
Glimpse Learning
Brand Design System — Visual Framework + Repeatable Templates
Turned a brand concept into a scalable design system covering logo direction, visual rules, style guide documentation, reusable templates, and consistent application across all documents and visual touchpoints. The system-first approach — rules before assets — means any team member can extend the brand without breaking it. Rejected the common logo + colour palette approach in favour of a documented token layer that governs every output.
ComfyUI Workflow System
Own KDP publishing
Style-Consistent Image Generation — ComfyUI Print Pipeline
Style drift is the usual problem with AI-illustrated books: page 12 stops looking like page 1. Here the look lives in the graph, not the prompt. The styler template, checkpoint and LoRA weights are fixed, so only the subject changes between pages. I also revived and cleaned up older workflows: fixed missing nodes and models after node-pack updates, removed dead branches, and laid each graph out in four readable stages.
AI Film Production Tooling
Independent film studio · NDA
AI Film Shot-Review System — Sheet-Driven Director Review
Every take sits next to the prompt that made it, and each decision is recorded in the sheet production already works from. There is no backend and no build step: it is one HTML file the team can open anywhere. The screenshots use invented demo data; the real production is under NDA.
Marketing Operations Platform
Glimpse Learning
GTM Analytics & Content Operations Platform
GA4, Search Console and LinkedIn share one date range with period-over-period comparison, and each post is tied to its campaign and tracked link, so planning and results sit side by side. The screenshots use a synthetic dataset; the live instance is private.
AI Film + Physical Installation
Oficina ID
Retail Signage System — AI Brand Film + Raspberry Pi Playback
Live at the booth since July 2026. In a full week of 12-hour trading days it ran with no incidents: the player restarts itself if playback dies, a hardware watchdog and a nightly reboot keep the Pi healthy, and content is changed remotely without anyone on site.
Real-time 3D / VR
Client project
VR Environments & Characters: Low-Poly Real-Time Assets
Five interior sets and six characters built for VR from the client's reference photos. The environments were modelled in Maya, textured with trim sheets in Substance 3D Painter and Photoshop, and assembled in Unity. The characters started in Character Creator; props were modelled in Maya and textures finished in Substance 3D Painter and Photoshop.
Skills & Tools
Product / UI / Design
Video / Motion
Collaboration
AI & Automation
3D / XR / Real-Time
Scripting / Data / Web
Education
Newcastle upon Tyne, United Kingdom
Master of Arts in Visual Arts (Painting)
Porto, Portugal
Bachelor of Arts in Painting
