L’Agogique

Strangely the “Agogique” Wikipedia article is in French only, here:

https://fr.wikipedia.org/wiki/Agogique

Thus I asked Oxford about “agogic”, I copy/paste:

1 An adjective indicating a variety of accentuation demanded by the nature of a particular musical phrase, rather than by the regular metric pulse of the mus. The first note of a phrase, for instance, may be felt to suggest a slight lingering which confers the effect of an accent: similarly, a leap to note significantly higher or lower than the preceding notes, or a strong discord resolving to a concord, may convey an effect of accentuation (by means of lingering, pressure, etc.) and there are other examples. The complementary term to ‘agogic accent’ (accent of movement) is ‘dynamic accent’ (accent of force), which implies the normal and regular rhythmic accentuation of a piece of music.

2 In a wider sense, ‘agogic’ covers everything connected with ‘expression’, e.g. rallentando, accelerando, rubato, pause, accentuation as described above, etc.

Well of course it’s a tool, a state of mind.

I read about this in a Sol Gabetta (a cello player) interview. If we follow the score, it’s gives a computer mood. One needs groove, or rubato, expression. And it’s linked of course (because we follow the sheet music score, right?) to the idea of “freedom blossoming on constraint”. And it’s linked to the two-to-tango idea of “singing melody seems free but it’s conducted”, enchanted and tamed at the same time.

“The interpreter juggles with spells”. Ces sortilèges sont l’agogique.

Of course we have to dig the “-agogy” word. Pedagogy. Andragogy?

And also, seeing this as a pattern for life, action, methods, rules, creation, art. Follow some rules but add some life, some “expression”, freedom into frames, etc.

Have a nice Christmas!

Instant Oyster or Tent? Repost

https://wp.me/p6yTGH-93x

How to make images with Artificial Intelligence with a few words, with ruDALL-E

Hi everyone! The “Prompt To Image” processes are blossoming everywhere on the web since Katherine Crowson presented the VQGAN+CLIP tool and made it public. This “Synthetic Imagery” (or GAN Art) was fantastic, but a bit difficult and slow to use.

You’ll find plenty of articles about this, and hundreds of “Google Colabs” with the code to play with. The result is often slow (about one hour to get an image).

The next step was to find similar tools (you enter a text, you get an image) on web pages like https://hypnogram.xyz, https://text2art.com/ or http://gaugan.org/gaugan2/ or the very easy https://www.wombo.art/ (have fun!).

There are tricks you quickly learn to use with each tool. Adding words to the prompt, like artists names or words like steampunk – here are bridges, a mantis, an owl, and for the first one “bird leather gold“:

Each site has its flaws, and one must use them to get things. For example, GauGAN2 is made for landscapes, so if you ask “Lake and forest” you get a realistic scenery. But if you ask “Totem” it’s lost, and there come the cool things:

The possibilities are infinite. Just give two words like “Airship Fire”:

Not what we expected, but good images, inspiring maybe if you write stories, poetry, or if you draw. Make 20 of them with automation and you’ll find a few great pictures.

oOOo

I made plenty of movies with these:

oOOOo

This year the Russians invented ruDALL-E ( https://rudalle.ru/en/demo ) and it’s different, more realistic, and MUCH FASTER than every other similar tools. It needs about 1-2 minutes to make one image.

The results are less “digital artist”, and much more realistic, because it’s trained on millions of photographies (an AI must be “trained”). This morning, today, I made a few dozens, like these 3:

Yessss possibilities are great. And you don’t have to write in Russian, they translate. Good.

oOOOo

This team made a BOT, which is on Telegram (yes, the app, it’s on your phone and your Mac, right?). You’ll find it on the page, it’s here: https://t.me/sber_rudalle_xl_bot

• On this bot, you use the ruDALL-E Malevich (XL) Model, which is very powerful.
• Each prompt gives you THREE images, you just have to save them on your computer, and it works on your phone too.
• You have to prompt in Russian. Therefore you have to use a translation tool like Google Translate to invoke it.
• If you find a good prompt, you can and must repeat it: each time you’ll get NEW images.

Here are images with the prompt “Airship in the mist”, which is “дирижабль в тумане”. I made 135 of the same prompt today. I’ll make a clip later. Here are 12 of them:

These are cool, right?

Here’s my YouTube channel with plenty of clips made with these: https://www.youtube.com/channel/UCkYi6dzJ5emaY0tPGat3k9Q

Have fun!

My last Shazam, in no particular order

Mantiskane makes instrumental music

I invented Mantiskane, a musical entity, a more electronic facet of my musiquettes. It’s maybe Mantis Kane, a guy from another planet, half-human half-mantis.

I made a clip with images I made with the GauGAN NVIDIA model, which is at gaugan.org. This tool is designed to create landscapes, but I tickle it with non-landscape-words, as it fits.

I made more than a thousand flying machines, chose a few dozens and made the music from a simple loop, a pile of sounds refusing to evolve. Piling.

QES Prototypes:

Then I added a “chorus”, a second part based on a military snare drum, it’s here:

QES Prototypes II:

oOOOo

Before that I did it with African mood, inventing a planet, composed a tribal music based on percussions and passing by sounds…

Quick-Eyed Memories:

oOOOo

Before that I worked with the VQGAN+CLIP model of hypnogram.xyz to create SF images. It’s a more “digital art” tool, right? I made an abstract music with a bunch of different slow loops on my Mac.

Space Gates & Titans:

oOOOo

Have fun! Thanks for reading!

Jean-Pascal