Hao AI Lab· @haoailab · X·· 4 天前AI 评分62
AI 导读
Hao AI Lab 推出的 FastH3 Omni 现已支持在 DGX Spark、RTX GPU 和 Apple MLX 上本地运行。其中单张 Spark 生成 5 秒 480p 视频耗时约 3 分钟、两张 Spark 约 2 分钟，FastH3 T2AV 在单 Spark 上耗时 52.6 秒、双 Spark 上耗时 30.7 秒。
正文 · 原文
(1/7) FastVideo FastH3 Omni goes local on DGX Spark, RTX GPUs, and Apple MLX 🚀
- FastH3 Omni, a 5 s 480p clip from a photo and a prompt takes ~3 min. On two Sparks, ~2 min
- FastH3 T2AV is 52.6 s on one Spark, 30.7 s on two Sparks
Blog: https://haoailab.com/blogs/fasth3-omni-local/
Cookbook: https://haoailab.com/FastVideo/cookbook/
HF 🤗 https://huggingface.co/collections/FastVideo/fasth3-omni
@NVIDIARTXSpark @NVIDIAAI @MiniMax_AI
Every clip in this video was generated on NVIDIA DGX Spark. 8-step NVFP4 checkpoint.
来源：Hao AI Lab · x.com