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. Veo 3.1 upgrade is now on Lovart

Veo 3.1 upgrade is now on Lovart

An upgrade demonstration project around Veo 3.1 integration with Lovart, showcasing the new model's incremental value in creative scenarios through image quality and motion performance examples.

Leo WangJanuary 18, 2026Liblib AI | EvokenAI书写AI VideoProduct Launch
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.

757K429189K406

The focus of this upgrade video is translating a model version bump into quality changes users can feel — not just saying "there's a new version," but letting the visuals themselves answer "is the upgrade worth it."

Background

Model upgrade content most easily falls into "version number marketing," but what creators care about is whether image quality, motion stability, and delivery efficiency have actually improved. The challenge is that pure parameter explanations lack perception, while pure case collages lack logic. So this video had to tightly bind "upgrade information" with "real differences."

Technical Details

Upgrade info bound to examples. Version copy and corresponding shots are bound one-to-one in post-production with matching entry and exit animations — preventing the disconnect of "copy says upgrade, but footage doesn't show it."

Unified color across subjects. Each case is pre-composited and then color-graded uniformly, ensuring viewers perceive differences coming from capability upgrades rather than post-production style variations.

Difference-emphasis editing. Key shots use brief repetition and local magnification — viewers can directly see the improvement in detail and motion without verbal explanation.

Summary

To tell an upgrade story well, the core is translating version changes into visible results. As long as the differences are consistently and clearly bound to the footage, viewers will naturally accept this as a meaningful capability upgrade.