LemonSlice has released Lemon Slice 2, a 20 billion parameter diffusion transformer model capable of generating infinite-length video at 20 frames per second on a single GPU. The company's API allows users to create and interact with photorealistic video avatars in real-time, aiming to become the dominant form factor for conversational AI. While acknowledging the challenge of the uncanny valley, LemonSlice claims their avatars are best-in-class and can also generate stylized cartoons and animals. The real-time generation was achieved through a causal model, sliding window attention, GAN-based distillation, and various inference optimizations. AI
IMPACT Enables real-time, interactive video avatars, potentially shifting conversational AI interfaces and raising concerns about misuse.
RANK_REASON The cluster describes the release of a new AI model with technical details and a demo, fitting the research category. [lever_c_demoted from research: ic=1 ai=1.0]
Read on HN — machine learning stories →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →