Huzaifa RafiqMotion Graphics Designer · Dubai
Home/Work/AI Video
// Expertise

AI video & generative motion

A full broadcast title sequence produced end to end with generative AI — and an honest account of the shots where AI still loses to a render.

An AI pipeline that has actually gone to air

Most AI video on portfolios is a test. The Season 2 title sequence for Menna Wa Fena is a full broadcast title sequence — luxury gold Arabic calligraphy on black marble — produced end to end with generative AI. Every frame, texture and light reflection. No Blender, no traditional compositing chain. It went out on a television channel.

Where generative video genuinely wins

Where it still fails

Hybrid is usually the right answer

The Cinematic Title Sequence from the same period is the counter-example: Blender 3D for the metallic typography and structure, with Runway ML supplying the smoke and embers around it. Structure and type where precision matters; generative where texture and atmosphere matter. That split is the working method, and choosing correctly per shot is the actual skill.

How I fit it into a real pipeline

Generative tools are a department, not a replacement. In practice: block the sequence traditionally, identify which shots are texture-led, generate those against locked reference, bring everything back into After Effects for grade, type and pacing so the sequence holds together as one piece. The output has to survive being cut next to traditionally-produced material without looking like it came from somewhere else.

Let’s make something move.

Open to full-time roles and select freelance projects — Dubai, the Gulf and remote. Showreel, breakdowns and CV available on request.

Email me CV & availability Watch the showreel