Archive for September 23, 2022

Friday, September 23, 2022 [Tweets] [Favorites]

Reshaping Text With rs

Dr. Drang:

The problem was that the lists were long. One had 84 items and the other had 30. Pasting them into the message in the form I had them—one item per line—would take up too much space. Pasting them in as a comma-separated series—which I could convert them to with a simple search-and-replace—would be very hard to read. What I wanted was nicely formatted set of rows and columns that would be easy to read without taking up too much space.

[…]

After some Googling, I came across this Ask Ubuntu question, which led me to rs, an old BSD command that comes installed on macOS. The name stands for “reshape,” and it will take any row/column set of data and rearrange it into a different number of rows and columns.

The Macintosh Portable Introduction

stirz:

On this day 33 years ago, Apple introduced the Macintosh Portable.

I just love how @gassee does the presentation: lots of humor and a live assembly on stage.

Compared with more recent Apple events, it almost seems humble.

I enjoyed this video.

Stable Diffusion Based Image Compression

Matthias Bühlmann (via Hacker News):

These examples make it quite evident that compressing these images with Stable Diffusion results in vastly superior image quality at a smaller file sizes compared to JPG and WebP. This quality comes with some important caveats which must be considered, as I will explain in the evaluation section, but at first glance, this is a very promising option for aggressive lossy image compression.

[…]

The main algorithm of Stable Diffusion, which generates new images from short text descriptions, operates on this latent space representation of images. It starts with random noise in the latent space representation and then iteratively de-noises this latent space image by using the trained U-Net, which in simple terms outputs predictions of what it thinks it “sees” in that noise, similar to how we sometimes see shapes and faces when looking at clouds. When Stable Diffusion is used to generate images, this iterative de-noising step is guided by the third ML model, the text encoder, which gives the U-Net information about what it should try to see in the noise. For the experimental image codec presented here, the text encoder is not needed.

[…]

To use Stable Diffusion as an image compression codec, I investigated how the latent representation generated by the VAE could be efficiently compressed.

Previously:

Midjourney and Stable Diffusion

Ben Thompson:

The initial roll-out of large language models seemed to confirm this point of view: the two most prominent large language models have come from OpenAI and Google; while both describe how their text (GPT and GLaM, respectively) and image (DALL-E and Imagen, respectively) generation models work, you either access them through OpenAI’s controlled API, or in the case of Google don’t access them at all. But then came this summer’s unveiling of the aforementioned Midjourney, which is free to anyone via its Discord bot. An even bigger surprise was the release of Stable Diffusion, which is not only free, but also open source — and the resultant models can be run on your own computer.

Divam Gupta (via Hacker News):

Introducing Diffusion Bee, the easiest way to run Stable Diffusion locally on your M1 Mac. Comes with a one-click installer. No dependencies or technical knowledge needed.

Steve Troughton-Smith:

Stable Diffusion on my M1 is kinda neat, but slows the system to a crawl for a minute or two while it processes. Stable Diffusion on my 3080 Ti, however, is blisteringly fast. 3 seconds to produce an image in a batch.

It sounds like it doesn’t yet use the M1’s Neural Engine.

Andy Baio (Hacker News):

As AI-generated art platforms like DALL-E 2, Midjourney, and Stable Diffusion explode in popularity, online communities devoted to sharing human-generated art are forced to make a decision: should AI art be allowed?

See also: Dithering, which had an interesting discussion of Midjourney’s Discord-based interface.

Author:

Previously: