Latest AI Models

Seaweed-APT2 is a streaming video generation model for real-time interactive applications. The model autoregressively generates a single latent frame (4 video frames) at a time, allowing the result to be streamed to the user with a minimum latency. Each latent frame is generated using only a single network forward evaluation (1NFE). With KV cache, the model can generate long duration videos. As a result, the 8-billion-parameter model achieves real-time, 24fps, nonstop, streaming video generation at 736x416 resolution (equivalent to 640x480) on a single H100 GPU. This is significantly faster than existing approaches.