Inspiration
This project aims to build an interesting dialogue system utilizing the characteristics of StreamDiffusion.
What it does
Users are not talking to a common Chatbot in English, but in a kanji-like fake language, where responses are rendered with diffusion-based models.
How we built it
We build this system based on StreamDiffusionIO, a modified version of StreamDiffusion that supports rendering text streams into image streams.

Log in or sign up for Devpost to join the conversation.