Leo
  • Posts
  • Projects
  • About
  • Posts
  • Projects
  • About
Bilibili抖音小红书

© 2026 XT. All rights reserved.

  1. Home
  2. Projects
  3. Liblib AI | Evoken
  4. Lovart Official Launch

Lovart Official Launch

Brand promo video · AE/PR · Lovart official launch film · storyboard + multi-layer UI compositing · full pipeline narrative · X/Instagram

Leo WangMay 12, 2025Liblib AI | EvokenAI书写AI VideoBrand Film
This is a work sample from my previous employment at Liblib AI | Evoken. I served as the video producer and retain the right of attribution under applicable law. Copyright belongs to the original company. This content is for personal portfolio use only, with no commercial or promotional intent.

More projects

  • Lovart: The AI Creative Partner for SMBs

    Lovart: The AI Creative Partner for SMBs

    Brand promo video · AE/PR · Lovart SMB feature launch · storyboard + AIGC (Lovart/Kling) · X/Instagram · 1.11M+ views

  • LibTV 720° Panorama Feature

    LibTV 720° Panorama Feature

    LibTV recently added 720° panoramic video generation — describe a scene in one sentence and AI produces a draggable spherical shot, sharply reducing the setup and iteration cost of immersive spatial storytelling.

  • Lovart Email Section

    Lovart Email Section

    In a marketing email, users glance once — this UI animation uses a fixed prompt bar plus a background asset collage to explain "one prompt, 40 brand assets" in a single frame.

4.3K16

This official launch video answers not "what can Lovart do," but "how do you walk the full path from brief to deliverable design" — planning, generation, editing, and delivery woven into one story that's easy to follow, replicate, and trust.

The Tension a Launch Video Has to Resolve

Too many capabilities, and viewers only remember "it looks impressive." A broken flow, and they don't know where to start. So the video can't stack result images or rely on raw screen capture alone — task understanding, tool use, result expansion, and manual refinement all have to live on one continuous narrative thread, so it reads as a production workflow, not a feature reel.

How the Visuals Hold the Line Together

Multi-layer UI compositing splits the recording into background process, key features, and subtitles. Unified motion and mask pacing connect modules into a continuous track, so nothing feels like an isolated demo. Between the brand and robot cases, we use "same interface skeleton + content swap" — the workspace stays put while task cards, assets, and results change, with subtle push-pull moves so the scenario shifts but the workflow doesn't.

The results section alternates grid expansion and close-ups: one image to confirm quality, then a multi-size, multi-asset array, then back to finished shots and a collage overview — detail and batch output visible at once.

What viewers should take away isn't a single dazzling frame, but a path they can follow: understand the brief → generate → edit → deliver. Next time they have a project, they'll know how to walk through Lovart step by step.