• 0 Posts
  • 27 Comments
Joined 2 years ago
cake
Cake day: June 7th, 2023

help-circle
rss




  • In those dark ages, lesser-known systems like QNX Neutrino and BeOS seemed impossibly fast and modern, and possibly represented the future of computing:

    A necessary challenge that QNX had to meet was the performance needs of a customer base primarily concerned with realtime applications. Although an elegant OS architecture is a joy to work with, “academic elegance” will not necessarily create a commercially successful operating system—it must also provide performance better than traditional monolithic kernel operating systems. […] For QNX to deliver the full performance of the hardware to the application level (and to exceed the performance of monolithic kernel operating systems), a number of architectural innovations were developed.

    https://www.youtube.com/watch?v=KDzxdv_MPJs












  • Looking forward to the performance improvements.

    What’s under the hood?

    The key driver of this advancement in composition for SDXL 0.9 is its significant increase in parameter count (the sum of all the weights and biases in the neural network that the model is trained on) over the beta version.

    SDXL 0.9 has one of the largest parameter counts of any open source image model, boasting a 3.5B parameter base model and a 6.6B parameter model ensemble pipeline (the final output is created by running on two models and aggregating the results). The second stage model of the pipeline is used to add finer details to the generated output of the first stage.

    Availability

    SDXL 0.9 is now available on the Clipdrop by Stability AI platform. Stability AI API and DreamStudio customers will be able to access the model this Monday, 26th June as well as other leading image generating tools like NightCafe.

    SDXL 0.9 will be provided for research purposes only during a limited period to collect feedback and fully refine the model before its general open release. The code to run it will be publicly available on Github.

    If researchers would like to access these models, please apply using the following link: SDXL-0.9-Base model, and SDXL-0.9-Refiner. Please log in to your HuggingFace Account with your academic email to request access. Kindly remember that currently, SDXL 0.9 is exclusively intended for research purposes.