Amazing effort by the entire FastVideo team! Super proud of how fast we are shipping! Open source must win!
More coming soon, RTX support, FastH3 V2, and Ref2VA support! 🚀
Special shout out to @nuvalab, and @NVIDIAAI FastGen and Enterprise Products Team for the joint effort!
Introducing MiniMax FastH3 on Reactor - the latest open-source model by @MiniMax_AI.
Stream 720p with audio at $0.007/second with first frame image support, faster and cheaper than ever.
Get started now by cloning our demo app: https://t.co/7qeQBgVZ2a
We just bring FastH3 to dgx spark and apple silicon!
Yes you can generate h3-level clips on your local MacBook or dgx spark!
Team is cooking so hard to bring this model to ALL!!
(1/7) Last week FastVideo released FastH3. Today we bring it local: @NVIDIA DGX Spark 💚 and @Apple Silicon 🍎through MLX. 8x speedup!
FastH3 now supported on NVIDIA DGX Spark and Apple Silicon! over base @MiniMax_AI H3 for local generation!
This 15 seconds 1344×768 clip was generated on two NVIDIA DGX Sparks. Fully local. @NVIDIARTXSpark@NVIDIAAI
🎬Video generation faster than playback!
🚀MiniMax H3 on vLLM-Omni + FastVideo's FastH3: a complete 10.1s MP4 - video AND synchronized audio - rendered in 8.7s!⚡️
Thanks to @MiniMax_AI for the great Minimax H3 release, the FastVideo team @haoailab for open-sourcing FastH3 and helping on the serving integration, and @NVIDIAAI for the continued sponsorship and joint optimization efforts!
Love the great work being done at @reactorworld!! They took our open weight FastH3 and built something amazing and also open sourced everything.
This is the right way to do open source! Open source must win!
Big shoutout to @taiuti@_bschmidtchen
45% preferred FastVideo FastH3 or are neutral compared with @MiniMax_AI H3.
Our open-weight FastH3 achieves 15s generation in 13s and 14x speedup. 🚀
Big shoutout to the folks at @fal and @isidentical for helping us run an eval against H3. As an open source project we always appreciate all the help we can get.
The entire team is quite excited by this result for a preview checkpoint trained on a fraction of our planned total compute and partial data. Excited for what our next versions can do!!
Weights: https://t.co/xMcHi0te0k
Blog: https://t.co/SBYKYq5tud
Thank you for your contribution to the open source H3 ecosystem @fal!
https://t.co/EHyNYZR5pG
(1/5) 5 seconds of video. 1.8s seconds of generation. One NVIDIA GeForce RTX 5090 on FastVideo. 🤯🚀
- FastWan-QAD, a new family of video generation models
- Trained with FastVideo's Quantization-Aware Distillation (QAD) recipe.
- Powered by FastVideo, we push a single NVIDIA GeForce RTX 5090 to its absolute limit: generating a 5-second 480P video in 1.8s end-to-end!
📜 Blog: https://t.co/xs7fPvbGuh
💻 Code: https://t.co/5YnBSko00N
💽 Model: https://t.co/NNbl9Og6bw
Honsle Zindagi ke dekhte hai.n,
Chaliye kuchh roz jee ke dekhte hai.n..
Neend pichhli sadi se zakhmi hai,
Khwaab agli sadi ke dekhte hai.n..
Baarisho.n se to pyaas bujhti nahi,
Aaiye zehar pee ke dekhte hai.n..
“The millions are awake enough for physical labor; but only one in a million is awake enough for effective intellectual exertion, only one in a hundred million to a poetic or divine life. To be awake is to be alive.” - Henry David Thoreau