{{site_title_here}}

Category: tech-experiments

  • Gemini (more than) edits your photos

    Gemini (more than) edits your photos

    Last Saturday night I had a blast photographing the Roseville Big Band perform at the Commemorative Air Force Fall Bombers Moon Ball. Trying to get more media for the Minnesota Mandolin Orchestra, I thought I’d ask Glen, who performs with both ensembles, if we could swap some photo ops.

    Context set, I was nervous during the shoot. I had walked the hanger during the day, but I wasn’t sure about lighting for the night of the shoot. Also, I had misunderstood the timing, expecting to have some time with the band ahead of the performance for a portrait. Actually, that was accurate, but I hadn’t planned for throngs of people arriving early at the hanger.

    By the time the band was ready for their photo, there were oodles of people crawling around Miss Mitchell, the aircraft that the band wanted to be photographed with. The sun was low — about 30 minutes from set and directly behind Miss Mitchell. There was a professional photographer already working with plane into his portraits whom I asked for a graceful pause.

    Unaltered photo
    Manually edited photo
    Gemini edited photo.

    Having to work quickly, I had the plan to use a 14-24mm lens and a camera-mounted fill flash and shoot close to crop out visitors. With the sky being so bright, the sun at the back of the plane, and the band dressed in black, I pushed the exposure a full step and clicked as fast as my flash would cycle.

    Thirty seconds later, I had my washed-out result, above left. To the punchline, this morning I read that Gemini can edit photos, though not NEF or TIFF today, and after several iterations, mostly of directions to brighten Gemini’s idea of a sunset and not to to distort the subject’s proportions, Google delivered the result on the right.

    If you’re not familiar with the band, it might not matter, but I doubt that many family members would recognize them in the AI-edited photo. Sandy walked up behind me and asked, “tuxedos! Is the conductor wearing the red one?” And I realized I couldn’t identify the conductor – actually, I thought he wasn’t present and I swore. Then looking at the faces, things didn’t look right. It was a hassle to brighten Gemini’s result, but I could not persuade Gemini to spare the band face lifts.

    There was value to complaining to Gemini. The AI-altered image focused my time spent on the exposure of the original image in NX Studio by giving me a target in my imagination. The center(and banner) image is the result.

  • My Introduction to Stable Diffusion

    For a few years now, I’ve been fascinated by programmatic art. For ten years or so, there’s been a stream of projects that do something along the lines of applying an artist-inspired filter (usually Van-Gogh) to existing photos to stylize them. Last year, the DALL-E project went a step further by generating images from textual descriptions and a library of images.

    I was stunned at both variations on existing images and images synthesized from descriptions. This summer, generative art got a little more accessible to the masses when Stable Diffusion was released, using similar technology, but publicly available models (at least for now).

    I think the business model leverages that you can make interesting images from the public models, but that most businesses will want to tune the image text-to-image models to suit their intended message. The models require an enormous amount of energy to train — the default one has an 11 metric-ton carbon footprint — and the model propagates cultural biases present in the underlying data. Both aspects seem significant enough to motivate an entrepreneur to hire out specialists.

    Stable Diffusion is a little tricky to install on a M1 Mac — you have to checkout a particular branch of stable-diffusion, currently `apple-silicon-mps-support`, and hope that nightly PyTorch builds are stable. You also have to register with HuggingFace to download an image model, which seem to be updated frequently at this point.

    There’s currently no GPU support for Apple silicon for Stable Diffusion, so you need to be patient, but here are some samples of the Stable Diffusion imagination…. that might sound a bit like “stable genius” and artistically sometimes the images resemble another product shoveled from a stable…. but again, samples of

  • Onyx Boox Max2 Pro

    Serving PDF

    Using the Boox to read sheet music, I have to adjust my workflow. Previously, I had used a web server, KWS, to provide set lists and sheet-music pdf files to the browser.

    The Boox seems to be highly optimized to conserve battery life, and perhaps as a consequence the web server freezes. I see this happen on my Pixel C, but relatively infrequently — about once every 6-8 hours of use on the Pixel C versus once every 10 minutes on the Boox.

    To make matters worse, the Boox is slow to switch and restart applications.

    Organizing PDF

    The Boox default view is a PDF browser, and it supports organizing files by directory, but the selection process is slow and cumbersome and is opaque in that it doesn’t correspond to actual directories.

    Another idea is to concatenate sheet music into a single-file set list. There are lots of programs available to concatenate pdf, and Apple Preview is one of them.

    Another option is to use a sheet music app running on the Boox, such as Fakebook, Orpheus, or Mobile Sheets Pro. I have used Fakebook before to read chord charts, but didn’t realize it could read PDF, too.

    While searching for Android sheet-music readers, I stumbled upon Musical Android, a site devoted to Android audio apps.

    Bluetooth

    After several tries, I was able to connect my Airturn Duo pedal to the Boox. The process was tedious in that the pedal requires long button presses to send to pairing mode, the Boox only infrequently updates the list of available devices, and the Boox usually displays the Bluetooth address in the place of the device title.

    December, 2019 update:

    The afternoon of a performance, while I was warming up for an orchestra holiday show, the Boox did its best brick impersonation. I scrambled to print out my sheet music before rushing out for the performance across town.

    I was eventually able to return the Boox to usable condition, but only after booting it into safe mode and losing all of my sheet music.