Kyohansha
Summary
Kyohansha is a web-based product delivering 60FPS Live2D AI avatars equipped with Lite-RAG long-term memory.
Similar Articles
LiveAnimate: Stable Long-Form Streaming Human Animation in Real-Time
LiveAnimate presents a 14B-parameter video diffusion transformer enabling real-time, long-form pose-driven human animation with stable streaming and constant memory usage via PR-Sink attention. Achieves 19.63 FPS inference on two H100 GPUs, maintaining quality over three-minute streams.
PersonaLive! Expressive Portrait Image Animation for Live Streaming
PersonaLive is a diffusion-based framework for real-time expressive portrait animation in live streaming, achieving significant speedups through hybrid implicit signals and autoregressive streaming generation.
Open-LLM-VTuber/Open-LLM-VTuber
Open-LLM-VTuber is an open-source voice-interactive AI companion with a Live2D avatar, supporting real-time conversations and visual perception, fully operable offline.
@dflieb: Fun demo of @KeyframeLabs' real-time video avatars. Have AI Garry and AI Dave talk about any topic, and drop questions …
Demo of Keyframe Labs' real-time video avatars where AI characters Garry and Dave can converse on any topic with live questions from chat.
I built a fully immersive AI agent with native time perception & group chat understanding, all with a single-pass logic.
The author built a fully autonomous AI agent named KawaiiBaka that runs in a Discord group chat, using a single-pass cognitive loop with native time perception and real access to execute Python on a Windows machine. The system uses Mistral API for the LLM and a local image generation pipeline to create context-aware selfies.