Guizang describes a daily AI news video workflow in Muse: curate notes and media, then use Pi with K3 and GLM 5.3 to assemble a video with guizang-product-video-skill and return it in chat. This is his own integration example.

歸藏(guizang.ai)
@op7418
关注人工智能、LLM 、 AI 图像视频和设计(Interested in AI, LLM, Stable Diffusion, and design) 歸藏的 AIGC 周刊|公众号:歸藏的AI工具箱
게시물
4Guizang updated his Skill for making software product videos from a codebase and real product components. He says Mimo V2.6 Flash produced a reasonable result in his test, though it did not match Opus 5.5.
Guizang announces an update to Humanizer-zh incorporating upstream changes and feedback from repository issues, and invites users to try it and report problems.
Guizang introduces Yingzao, his Skill for turning real travel and cultural-place photographs into editorial posters. The Article shows single-photo and multi-photo examples, cultural annotations, optional before-and-after comparisons, and an optional video storyboard. He recommends using Codex with GPT-image 2.0.