FastVideo Supports the Open-H3-Regenerate-2K Model
Hao AI Lab announced that FastVideo now supports the Open-H3-Regenerate-2K model from HaoZhe65347 and NVIDIA AI, and provided a link to the 2K model. The series previously covered FastVideo's inference optimization of MiniMax H3 Flex, open-sourced by Pika Labs: on a single GB200, generating a 5-second 480p video with audio takes 5.8 seconds, up to 7 times faster than the official open-source inference code, with newly added multi-GPU support.
Why read this
SelectedAI score 66
FastVideo's inference optimization for H3 Flex provides measured latency across multiple quantization levels and multi-GPU setups, which can be compared against the official code to assess the speedup.
Topics
Body
(5/6) And now 2K. Open-H3-Regenerate-2K from @HaoZhe65347 and @NVIDIAAI is supported in FastVideo.
2K model: https://t.co/kAOpriDDbg