Node-Based Storytelling: Mix Text, Images, Audio, and Video
Imagine crafting a story like a mind map: each node can hold text, images, audio, or video. This research introduces a node-based editor that turns multimodal storytelling into flexible, AI-assisted creation.
What it lets you do:
- Edit any node directly or with plain-language prompts.
- Auto-branch alternate plotlines for parallel storylines.
- An AI task-selection agent routes requests to specialized generators (story writing, structure reasoning, diagram formatting, context).
- Iteratively refine your narrative with precise, node-level control.
Early results show stronger control over story structure and smoother generation across text, images, audio, and video. Limitations remain: scaling to long narratives and keeping details consistent across many nodes. Next steps include human-in-the-loop and user-centered creative tools.
Authors: Alexander Htet Kyaw, Lenin Ravindranath Sivalingam. Paper: http://arxiv.org/abs/2511.03227v2
Paper: http://arxiv.org/abs/2511.03227v2
Register: https://www.AiFeta.com
AI Storytelling GenerativeAI Multimodal CreativeTech HCI Video Audio Images Text Research
