search
SparkDiffusion
Trends
- 1Peking University, Tsinghua and Alibaba open-source SparkDiffusion for faster video generation▼Peking University, Tsinghua and Alibaba Open-Source SparkDiffusion for Up to 265x Faster Wan Video Generation
Researchers at Peking University and Tsinghua University, working with Alibaba, have open-sourced SparkDiffusion, a new method said to speed up Wan video generation by up to 265 times. The release gives developers free access to the technique, which could make AI video generation significantly cheaper and faster for real-world applications.
- 2Peking University, Tsinghua and Alibaba open-source SparkDiffusion video AI accelerator●Peking University, Tsinghua and Alibaba have open-sourced SparkDiffusion, an AI video generation accelerator. The framew
Peking University, Tsinghua University and Alibaba have released SparkDiffusion as an open-source framework that dramatically speeds up AI video generation. The tool cuts Wan 2.1 video generation time by a factor of 265, reducing it from 4,769 seconds to 18 seconds on an Nvidia RTX 5090 GPU. Code and model weights are freely available on GitHub and Hugging Face, letting developers adopt the accelerator immediately.