Ai text-to-image | examples

↓|

↓|↑

↓|↑

↓|↑

brilliant right AI | hand

this image is not a photo, but the rendering by #midjourney text-to-image #AI. it is in many respects amazing. for example the light, shadows and reflections, the furniture, the face of the boy, the hair — all perfect. the concert guitar has a few flaws which are not obvious when looking at the image from a distance. the main problem with text-to-image AI are the hands. in this case, the right hand shows AI going one step further: the right hand is playing the guitar with proper finger picking, and we even see the thumb! normally, AI displays hands with three or five or six straight fingers. the boy‘s left hand has the usual problems. buttom line: the AI hands get better, they are much better than a year ago.

text-to-image AI

typical AI hands:

KI | vita

das bundesverfassungsgericht hält künstliche intelligenz für gefährlich für den datenschutz und den schutz der privatsphäre, vor allem beim bilden von personenprofilen durch die polizei. eines der argumente ist, dass die KI innerhalb von sekunden komplette biografien entwickeln kann.

in den drei beispielen unten antwortet chatGPT auf meine bitte, mir eine kurz-vita über die person maximilian schönherr zu schreiben. wenn ich diesen text auf mich beziehe (viele menschen mit diesem namen gibt es nicht), stimmt in dieser ersten version fast nichts. aber die vita ist so perfekt formuliert und hat ein flair, sodass sie leicht gespenstisch wirkt.

das problem dabei ist, dass man nicht mehr unterscheiden kann, was stimmt und was nicht stimmt. wenn ich zum beispiel den bot bitte, meine lokal berühmte freundin → lioba albus zu beschreiben, stimmt manches, vieles aber nicht. lasse ich ihn meine weltweit berühmte freundin → louise lecavalier beschreiben, stimmt alles. ich vermute, dass chatGPT versucht, der wahrheit nahe zu kommen. aber er deklariert an keiner stelle seine unsicherheit. wenn er mich am 7. mai 1985 auf die welt kommen lässt, stimmt das nicht. falls er jemand anderen mit meinem namen meint, deklariert er das auch nicht.

KI schreibt eine vita

auch bei einem anderen „seed“, also einer neuen auf zufall basierenden version, bleibt die KI dem thema treu: musiker, komponist. das geburtsdatum wurde vorverlegt, und der lebensmittelpunkt nach berlin bewegt:

zweite version

bei der dritten version kehrt der bot wieder nach wien zurück:

dritte version

god is a | charlatan

i fed these words from lana del rey‘s marvellous song “A&W“ into the text-to-image #AI #midjourney. it produced several results, one of which is the one below. i wanted angels and drones in the image. i find no angels. i wanted the image to look like a painting from the chinese han dynasty.

the charlatan with drones and gadgets.

young and sad and | old and sad

not happy when young, very sad when old.

i created these two images with text input and #AI. both images have flaws, but in general they are excellent examples for graphic design, stock photography e. a. i could merge the two images into one which would probably look mysterious, if not horror like. i could instruct the AI to re-render the image with another “seed”, which is basically the starting point of the randomized process. but currently i’m in the process to check out different scenarios, and i need to be cautios with my paid access to the #midjourney bot.

pseudo sexy | spams

vier spams vom wochenende. solche „sex“-nachrichten sind seit einigen jahren seltener geworden. deswegen lohnt es sich, sie aufzuheben. die angegebenen web-links sind alle falsch; sie führen wo ganz anders hin, nämlich auf webseiten, die dem opfer viren unterjubeln, mit allen möglichen, oft drastischen folgen. interessant finde ich, dass die fake-adressen alle http zeigen, statt dem seit längerem üblichen https.

spams, die zu üblen webseiten führen

the beatles on | bikes

i asked #AI to show me a rural midday scenery with the four Beatles, with long hair, riding on their bikes. for a first attempt not bad at all. ringo, followed by paul, john and george.

the beatles on their bikes. text-to-image AI

before that i had asked #midjourney AI to visualize john lennon on a bike in a messy abbey road studio. the bot delivered an amazingly complex, chaotic scene with someone (not john) on the drums and certainly no bicycle:

wide angle AI studio visualisation.

let’s be | raw

everybody’s perfect, nobody’s fine

i started this song with nonsense in mind. however, it turned out much “deeper”. the chorus is merely a wordplay, but in the context of the rest, it gains a bit of weight.

let’s be raw. (licensed via GEMA, germany)

We put on a mask, hide our true selves / Let’s pretend everything is alright / Deep down we all struggle and fight / And hope to find some peace inside / So, let’s be real, let’s be raw / Embrace the flaws and all the scars / For we all are imperfect stars / That’s what makes us who we are / Nobody’s perfect, everybody’s fine / Everybody’s perfect, nobody is fine / Everybody’s perfect, everybody’s fine / Let’s put on our masks / Hide our true selves / And pretend everything is alright / In this world of black and blue / We often feel so lost and confused / Our struggles pile up / Leave us defeated and used/ Nobody’s perfect, everybody’s fine / Everybody’s perfect, nobody is fine / Everybody’s perfect, everybody’s fine

DAW screenshot (cubase). click to enlarge.

the chorus appears twice, and in both instances my daughter sings the second half. there are 5 audio tracks in this song, due to the use of vocal harmonies. for example, i doubled parts of my voice in the verses using a slight formant change. the snappy bass and the main pad come from izotope iris 2, the drums from toontrack EZdrummer 3. the hammond organ is the B4 by native instruments. for the vocals i used waves harmony. this plug-in is not easy to handle with chord changes, but fun to use.

the watercolour painting above was created with (my) text input and the help of midjourney AI.

subwoofer | kids

a text to image experiment using midjourney Ai. i wanted a small subwoofer and lots of schoolkids. the subwoofer is not exactly small, but definitely soundproof.

kids at school, and a subwoofer.

below are a couple of variations, all done by the Ai within seconds.

midjourney | Ai

fictional downtown manhattan scenery.

i created this image from text. midjourney Ai did a marvellous job here. below you see the first four variations. i picked the buttom left for upscaling.

the train | stops

the train stops.

this is my first song with quite extensive use of automated vocal harmony. i used waves’ harmony for the polyphonic voice handling. the lyrics are about a triangle relationship, a train stopping and the middle of life, the middle of a maze. the image above was created using text-to-picture Ai.

There’s a wall between you, your lover and me. / There’s a well between your lover and me. / Wait a minute: The train stops! / Wait a minute: The train! / But when I turn round, I see the mirror, / And in the mirror there is a face / Of the girl I never knew. / A girl I’ve never seen before, / I’ve dreamed of so many times. / Yes, I’ve told you there’s a wall / Between you, your lover and me. / (That’s not quite true.) / There’s a wall between you and me, / Your lover and me / In this bigotomy (?) of our life. / We’re in the middle of our lives. / We’re in the middle of our days. / We’re in the middle of our maze. / But when I turn round, I see the mirror, / And in the mirror there is a face / Of the girl I never knew. / We’re in the middle of our days. / We’re in the middle of our maze.

does Ai | understand?

this is a photo i fed into #dalle2, an artificial intelligence portal:

original. photo: ms/dpa

below is one of four Ai variations. does Ai understand the concept at all?

Ai variation of the photo above.

yet another variation:

thin | air

new york in thin air. drawing by van dyke and others.

i composed this song about thin (and still) air today. the chorus ends with love in a cave. the piece has rap and rock elements. apart of singing i played all instruments on my midi keyboard. c minor. iris 2 is the major VST instrument. the drum sounds come for EZdrummer 3, most of the drum patterns from unison audio.

thin air. by ms. licensed via GEMA

elektrisch | schnellladen

nach 10.000 elektrisch gefahrenen kilometern, davon die letzten 3000 km bei winterlichen temperaturen, sehe ich manches gelassener. ich weiß aus reichlicher erfahrung, dass ein akku lieber dann aufgeladen wird, wenn er schön warm (aber nicht zu warm) ist. ich weiß auch, dass ein über 80% geladener akku unter stress steht und ich ihn deswegen auf 90 oder 100% nur dann auflade, wenn ich danach eine längere strecke vorhabe. ich weiß, dass langsam laden (in meinem fall innerstädtisch öffentlich und ohne wallbox) völlig okay ist und plane das gern in meinem zeitplan ein.

und ich weiß auch, dass für die ladegeschwindigkeit neben der akku-temperatur der aktuelle ladestand entscheidend ist. das zeige ich mit diesen drei bildern von gestern:

autodisplay: laden von 17 auf 80% in 36 minuten

ich hatte 12% akkuladung, als ich am schnelllader an einer autobahnraststätte andockte. die außentemperatur war 3°C. vermutlich war der akku gut vortemperiert, denn ich hatte dem wagen die ladestelle als ziel eingegeben. mein wagen hat mit winterreifen im winter eine reichweite von etwas unter 300 km, mit sommerreifen bei höheren temperaturen deutlich über 300 km. das foto oben zeigt die reichweite von 49 km beim akkustand von 17% und eine geschätzte ladezeit von gut einer halben stunde.

als ich zu laden begann, liefen 140 kW in den wagen, bei 21% ladung waren es immerhin noch 113 kW. das sind gute zahlen für diesen wagen, der offiziell maximal 130 kW strom aufnimmt. zum vergleich: die typische wallbox zu hause liefert 11 kW, die meisten öffentlichen ladestellen im innerstädtischen gebiet 22 kW.

display der ladesäule: solide ladegeschwindigkeit mit 113 kW

auch bei 72% fand ich die ladegeschwindigkeit recht ordentlich: 47 kW.

gegen vollladung wird es langsamer.

die geschätzte ladedauer von 36 minuten hielt der ladevorgang ein. sie stimmt meistens. achso: auch das weiß ich inzwischen — 12% akkuladung lässt mich nicht unruhig werden.

july’s | past

lots of traces

i composed this song with my guitar, some violins and cellos, a double bass and drums. the vindaloo part goes back to a real scene in khan’s restaurant in notting hill, london.

july’s past

panhandle | family

in 1987 i decided to visit the US branch of my family. we never met before and had exchanged more or less trivial christmas cards since i was a kid. i was greeted with a very warm welcome. my late aunt trudi lived in a trailer in the middle of the forest in north florida, the so called panhandle. her ex-husband johnny in another trailer 100 or 200 meters away. lots of dogs around.

trudi and i

trudi had three children, one of whom was sylvie. sylvie and i were almost the same age and very close. she then lived in a wooden house with her husband john.

the wooden house, my guest home

i visited often, mostly after a couple of days in manhattan, via pensacola where my relatives picked me up from the airport. i stayed in sylvie’s beautiful wooden house. my bed was on the top floor. the contrast between new york city and rural north florida couldn’t have been bigger. most people i met in that part of florida were pretty much right wing, although they insisted they were no rednecks. my aunt drove an old car she got from the local sheriff. it was so cheap because a corpse was found in the car while it was still in the sheriff’s hand. my cousin wore a t-shirt with the letters “english for florida” – which was targeted to/against cuban immigrants. there were barely any cubans in sylvie’s part of florida, most of them working very hard.

at one point, sylvie’s sister silke visited for a couple of days, with her toddler jasmine. with sylvie’s little brother henry i drove to new orleans for a day or two. in 1992 i took my wife there, in a cessna 172.

in trudi‘s trailer. red eyes were typical in flash photos.

john had studied agriculture at university and taught me a lot about farming, harvesting machines and sawmills. at me third visit he provided me with an old chevy van, so i could move around freely. the van was robust, but the brakes had very little grip.

with john, fishing.

in the nearby town defuniak springs i learnt to fly single propeller airplanes. in the photo below i‘m in the middle of a pre-flight check. i received my PPL (private pilot license) in 1990, and sylvie made a suprise party in the evening. she hated flying but permitted me to take her up for brief flight. the flight took maybe 3 minutes because she got airsick right after takeoff.

preflight check on a cessna 150

the man who ran the airport when i started learning to fly was a kind and modest man named charlie. soon he handed his little business (no landing fees, no tower, but a nice restaurant) to an ex-military helicopter pilot named walter and his wife maria. walter was an amazingly skilled pilot who wanted me to learn to fly helicopters. he treated his wife badly. i lost my interest in the defuniak springs airport.

sylvie getting ready for a ride in her car.

my cousin sylvie suffered from depression and took her life on 9/11 2006. her last email to me was from two weeks earlier.

sylvie’s ex-husband john runs a natural burial ground now.

sylvie‘s father johnny published several books, radioplays and audiobooks under the name john aalborg.

marie and the | water tower

photomontage using the water tower by theTechnician27 – wikimedia

i wrote and composed and sang this 1 minute song today. it’s about a woman in a dusty office suit, standing day and night below the water tower of a desolated town. the music consists of three VSL instruments, namely a piano, a violin and and oboe. the bass comes from super 8, the drums from EZdrummer3.

marie and the water tower

the song is licensed via GEMA, germany.