Process and Output

So I’ve had some good raw generations. The process I’m doing here is a variation on the process I had in 2019. I start with a photo I’ve taken, and I feed that into a caption generator and a prompt generator (I might add a third caption generator to the list like Flickr8 but CLIP Prefix / Interrogator has been decent). I play with the settings available to me, generally temperature and top_k until I get something back that I think is interesting.

some very early raw output that is too repetitive.

I run the same prompt text several times to get back a bulk of output. I then look through that raw output and pick out a few specific lines, which I then re-feed back into GPT-Neo. Again I adjust the settings until I feel something interesting comes back. I might do this 2 or 3 times. After I comb through all the output and start editing things into small vignettes. I found that using the single line captions from clip prefix, or editing a sentence together from Interrogator worked better as GPT-Neo prompts that plunking in whole word salads.

One thing I’ve noticed is that I didn’t need as much data as I thought I would for this process. In my original write up I was going to use my journals, and planning docs, and caption output, and I still might…because I spent the time sorting them, but I have a lot of good material to work with just out of prompting GPT-Neo with captions and I’m starting to feel that including too much extra text would just dilute my process.

I also found I didn’t need as many photos as I thought I would, mostly because I’m doing a manual process vs fine-tuning or something more automated. So part of this project has been just sorting. Sorting my photos, manually deciding what to keep, what to use, what to discard. Sorting through planning docs and picking out specific phrases. Sorting through raw output text.

notion database showing image sorting
What my image database in notion looks like

Its like excavation of my personal archive. Its enjoyable, and I feel its a deliberately slow way of working during a time when so many things want to go FAST. Maybe something to consider going from here is how to develop more methodologies to work slowly with AI.

Arrival and Week One

After a long day of flight delays I finally arrived at the Banff Centre to do a 5 week residency called Digital Promises.  The first week was mostly meet and greet, getting to know my cohort, and getting setup in my studio. Which I have to admit is pretty amazing. I’ve never had a space like this in my life, not even in grad school. It was weird deciding what kind of kit to bring with me. But I decided in the end to bring some specific IoT items I use a lot.

The project I’m working on here is building a depressed alexa, and I’ll talk more about that in future posts. But its basically a second iteration of one of my thesis prototypes called SAD Blender. Its nice coming to a residency with something I’ve already started, because it gives me some wiggle room to read, and document, and focus on where this might go, versus just always producing.

The other nice thing is that we share the floors with the BAIR artists who are here doing self directed work. Its a good cross section of people.

Panoramic of studio at Banff
The View

Anyways. Its pretty amazing. We didn’t really get into working mode until Friday, but that’s fine. Its good to get an info dump / people time off the bat now and then.