Digital sailing

 Due to receiving news of a new feature update, I visited the website to test NotebookLM. Developed by the Google team, this tool allows AI to analyze the content and summary of articles. Currently, the beta version is only available to users in the United States. This tool can obtain content for analysis through inputting text and files. Therefore, logging into a Google account to allow access to Drive data is a convenient method. Currently, it may still be in the early stages of development, and the interface design is not very user-friendly. Here, I am documenting my operating process so that those interested in trying it out can also give it a try. Step 1: Create Project Upon entering the project, the first thing you'll see is the Note page. You can directly type and add notes here. However, during my testing, manual input did not have the line break functionality. Step 2: Add source Switch to the Sources page and add a document. It can read files on Drive, accept PDF files, or

Out of curiosity, I attempted to reinstall stable diffusion. I had tried it once before in May 2023. In just a short span of 7 months, there have been many developments and changes, especially regarding the limitations on free resources in Colab. The web UI I originally used was challenging to complete the installation. As a result, I unexpectedly discovered a testing program that significantly enhanced my understanding of Colab and stable diffusion. Tosh Velaga shared his sample program. The information about "cache_dir" mentioned in it is very useful to me. When I was trying to install the Web UI, I set everything that could be stored to Google Drive to comply with Google's resource limits. When a session is interrupted, I only need to reinstall the VM, saving at least half of the time. I also noticed the need to choose the appropriate runtime type, providing sufficient GPU computing power. Due to the desire to switch models, I found technical documentation and resource