@xingbugengming: The finished video is out, feel free to check it out. The footage before 9 seconds is entirely made by Omni, the segment from 9 to 19 seconds is made with Codex and Remotion, and the rest is all actual recorded footage. The launch of Qianwen Office is to compete with Tencent's WorkBuddy, since it can directly access its own Taobao and 1688 e-commerce data sources, so it's estimated that everyone in e-commerce will need one in the future...
Summary
This post showcases video clips made by Omni, Codex, and Remotion, and discusses how the Qianwen Office product competes with Tencent's WorkBuddy, highlighting its feature of directly accessing Taobao and 1688 e-commerce data sources.
View Cached Full Text
Cached at: 08/26/26, 09:43 AM
Here’s the finished product, feel free to check it out:
The visuals up to the 9-second mark are entirely created by Omni, while the segment from 9 to 19 seconds was produced using Codex+Remotion. Everything after that is actual recorded footage.
The launch of Qianwen Office (千问办公) is clearly aimed at competing with Tencent’s WorkBuddy. Since it has direct access to its own Taobao and 1688 e-commerce data sources, I reckon it might soon become a must-have tool for anyone in the e-commerce business. https://t.co/YaODaXZWz3
Xiao Qi (@xingbugengming): This video was 100% produced using Remotion. Although it may look simple, the production process was quite complicated.
There are many details that needed fine-tuning. Sometimes it couldn’t quite handle the Bézier curves well, and as you can see, the text and animation effects in the video aren’t perfectly smooth yet.
But the biggest surprise is that it can perfectly replicate Qianwen Office’s input box 1:1, including all the widgets and the layout.
Similar Articles
@Zesee: https://x.com/Zesee/status/2072417062165635433
This article introduces how to combine the Codex AI programming agent and the Remotion video rendering library to code and modularize the video production process, enabling daily updates for self-media creators. The author shares a complete methodology from script structure and template design to daily workflow, helping creators free themselves from repetitive labor and build a video production pipeline.
@Sixtimenight: https://x.com/Sixtimenight/status/2086079773793833216
Introducing a Jianying short-video mass-production workflow: use Codex to copy existing manually tuned templates, operate Jianying drafts via VectCutAPI and jianying-editor-skill, and replace one-by-one generation from scratch, enabling batch production and automated publishing.
@iluciddreaming: Build a 'Video Content Factory' on Codex – Install These Plugins to Turn Text into Videos: HyperFrames – 'Ideation', Creative Planning; ElevenLabs Skill – 'Voice', AI Dubbing; Remotion Skill – 'Motion', Procedural Animation…
On the Codex platform, using plugins like HyperFrames (ideation), ElevenLabs (AI dubbing), Remotion (procedural animation), and Captions (subtitles), you can build an automated pipeline that turns text into video.
@yanhua1010: I never had high expectations for domestic AI Agents, until this time it did something that surprised me. I asked Tencent WorkBuddy to do a competitive analysis, and it dispatched an entire research team, with one AI specifically for review. It sent back the report written by its colleagues because a number in it had no verifiable source...
A user shares their experience using Tencent WorkBuddy for competitive research. The AI deployed a research team, and a dedicated review AI caught a number without a source, rejected the report, and had it redone. The final output was a presentation-ready slide deck.
@FuSheng_0306: Tried another plugin of Codex: Remotion. Codex+Remotion, made a 15-second tech-style video right away. The biggest takeaway is that Remotion can achieve more precise frame-level adjustments than Hyperframes, but Hyperframes is better at understanding plain language instructions…
A user compared two Codex plugins for video creation, noting Remotion offers more precise frame-level control while Hyperframes better understands natural language instructions.