@songhan_mit: Explore SANA World Model, using hybrid linear attention, efficient and fast!
Summary
SANA World Model is a new AI model that uses hybrid linear attention for efficiency and speed.
Similar Articles
@songhan_mit: the causal version of SANA world model is released, enabling close to real-time inference on a single H100:
The causal version of the SANA world model has been released, enabling near real-time inference for video generation on a single H100 GPU, with open-source code and a demo.
SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation
SANA-Video 2.0 introduces a hybrid linear-softmax attention mechanism for video diffusion transformers, achieving high-quality video generation up to 720p on a single GPU with significantly reduced latency compared to full-softmax models, while maintaining competitive VBench scores.
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
SANA-WM is a 2.6B-parameter open-source world model that generates high-fidelity 720p minute-scale videos with precise camera control, achieving industrial-level quality while significantly reducing computational requirements.
Efficient-Large-Model/SANA-WM_bidirectional
SANA-WM is an efficient 2.6B-parameter open-source world model for minute-scale video generation with precise camera control. It uses a hybrid linear diffusion transformer and a two-stage pipeline to produce 720p videos from images and text prompts.
SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
SANA-Video is a small diffusion model that efficiently generates high-resolution, long videos using linear attention and a constant-memory KV cache, achieving competitive performance at dramatically lower cost and faster speed compared to existing models.