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 ChatCanvas

Lovart ChatCanvas

A demonstration project around Lovart ChatCanvas, showcasing real-time collaboration between chat-driven creation and canvas to illustrate an integrated workflow from idea to finished visual.

Leo WangAugust 13, 2025Liblib 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.

10.0K125

ChatCanvas raises a practical question: on one canvas, can creators chat and iterate on a visual direction at the same time?

The Hard Sell Isn't "Can It Generate" — It's "Can You See the Collaboration"

Show only the final frame, and the collaborative feel vanishes. Show only the click path, and efficiency looks overstated. This video had to put input, system feedback, and iteration on one narrative thread so viewers could judge whether it fits everyday revision work.

How Post Production Makes Collaboration Legible

Split-screen UI compositing. Chat recording and canvas recording on two channels, with a Null unifying position and scale so both sides stay in rhythm during camera moves.

Keyframe-driven iteration nodes. Each round of input and output gets a timeline Marker; cuts and speed ramps follow the Markers, turning continuous feedback into clear steps.

Linked text and highlights. Shape Layer highlights on keywords, expressions bound to text layers — the focus stays on the current action even as the frame moves.

The lesson for collaboration videos: film the process as a readable workflow, not a stack of results. When input, feedback, and iteration are clear, viewers accept it as something they can bring into daily creative rhythm.