At PyTorch Conference today. Learning a lot about optimization techniques, compilers, domain specific languages -- the kinds of things that folks like @MachgenAI use to make lightning fast video generation.
1–0. Let's go, Valks 🏀💜
We tested @GeminiApp Nano Banana 2.1 all week, so of course we made something for MachGen hometown WNBA team, the @valkyries.
Now live on MachGen. Show us what you make!
Interested in lightning fast AI inference and efficient training? I will be at Triton Dev Conference tomorrow. Catch up with me me to talk about fast and efficient diffusion model inference and fine tuning with @MachgenAI
https://t.co/7EO8pK730E
I will be at one more #LATechWeek event today. "From Story to Revenue: How AI Is Reshaping Microdrama". I am looking forward to learning how the creative community think about short form video. @MachgenAI makes it quick and cheap to iterate on AI but style and content still rule
I'll headed to The New Rules for Video Marketing #LATechWeek. Please DM me if you want to chat about how @MachgenAI makes video, image, and audio AI faster and cheaper so you can get better results.
MiniMax H3 was open-sourced two months ago and the @MachgenAI team has been busy building cool features on top of it.
H3 is no longer only one model but a collection of different pipelines & accelerated LoRAs. Sharing a few things that our engineering team built on top of Minimax-H3 🧵