video1.0<iframe src="https://www.loom.com/embed/4904dced278248c88990722294b3f015" frameborder="0" width="1112" height="834" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>8341112Loomhttps://www.loom.com8341112https://cdn.loom.com/sessions/thumbnails/4904dced278248c88990722294b3f015-4def3fe692bf4e95.gif275.04In this video, I present a demo of my AI-based multi-agent video generation pipeline, which outputs a detailed promotional video plan in the form of a JSON script. The script includes scene-wise plans, voiceover text, visual direction, and reference images, all generated by an LLM-powered planner and scriptwriter. I've already saved a plan and generated a script, which can be used to create a 10 to 15-second promotional video. I aim to enhance the system further by enabling a direct call to my video generation pipeline hosted on Flask. I encourage you to explore this framework and provide feedback for improvements.