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 Social Media Short Video: Pet Cat IP

Lovart Social Media Short Video: Pet Cat IP

This Lovart social media short video revolves around turning pet cat photos into Peanuts-style comic art with one click, using conversational demos and batch meme results to showcase reproducible character IP output.

Leo WangMay 7, 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.

Social teams hit this scenario often: one pet cat photo, and you need a full set of on-brand memes ready to post. This video shows how Lovart handles it — straight and practical.

The Hard Part Isn't the Image — It's Proving You Can Keep Going

One nice result looks like a lucky hit. Model talk alone hides the real production rhythm. Social content needs constant updates, so a single demo doesn't convince — in under a minute, the video has to prove two things: the character stays consistent, and the expressions scale in batch.

Three Production Moves

Dual-track input and output compositing. The prompt UI and generated results sit on two main tracks, alternating at a steady pace so viewers naturally read the input → output link.

Character consistency check shots. Multiple outputs of the same character share one composition template, sequenced with position and scale keyframes — consistency is visible at a glance.

Progressive output layout. Single image, then a row, then multiple rows — same grid system with layered fades, so "scalable" becomes visual evidence, not a claim.

The reusable pattern: write the need as one actionable sentence → alternate process and result to prove repeatability → scale up layer by layer to show batch output. Model capability becomes a workflow ops can copy.