It’s finally here! 🎊
We open sourced our #vtuber motion capture solution at #GoogleIO!
Our new MediaPipe model predicts 478 face landmarks + 52 blendshapes from your webcam and is compatible with any ARKit rigged avatar! 😺🧵
Introducing Sora, our text-to-video model.
Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions.
https://t.co/YYpOAcrXQ3
Prompt: “Beautiful, snowy Tokyo city is bustling. The camera moves through the bustling city street, following several people enjoying the beautiful snowy weather and shopping at nearby stalls. Gorgeous sakura petals are flying through the wind along with snowflakes.”
@skalskip92@huggingface I can’t imagine it can perform real time on mobile if it’s about 27 mAP on a NVIDIA v100 🤔, and really needs TFLite Converter before useful for mobile or edge applications.
It still feels like a dream.
Yes, I am working on #Vtuber tech at Google AI!
💪😎💪
Our new BlazePose GHUM Holistic model predicts full body and hand joint rotations for 3D avatars. Available soon at https://t.co/X6nWTWdkqa. 🐎💃🎵
Paper and live demo at @CVPR for #CVPR2022.
Thanks for all the congrats messages. It’s hugely humbling. What a group of very nice people and business. Thrilled to be a part of it 😀🎉 #sbswinnershour
@BritishCrafting We’ve created an #ai auto tracking robot that removes the need for a camera person/videographer as it follows a person through machine learning. It’s currently on pre-order with Indiegogo after a successful Kickstarter campaign #sbswinnershour