KI zweite Runde

 

In meinem ersten Artikel habe ich mir Gedanken über die Faszination und die Gefahren von KI-generierten Bildern gemacht. Nun habe ich ein kleines Experiment gestartet, um via KI bessere KI-Bilder zu erzeugen. Das tönt zuerst mal etwas schräg. Es geht so:


Um ein Bild via KI zu generieren, muss man einen Bildbeschrieb formulieren – den sogenannten «Prompt». Bei Midjourney, der Plattform, auf der ich meine Prompts eingebe, habe ich folgenden Text formuliert (mit Englisch erzielt man bessere Ergebnisse):

Photograph of old buses in a busstation with a woman sitting in one of the buses looking out of the window with waterdrops on the window. The woman has black hair and a face with a sad expression, industrial area, night, cold colors except inside the bus with the woman, the photograph should look like a painting of edward hopper but ultrarealistic. The picture is taken from outside the bus. In the picture you can see the whole bus and other buses in the background. drone shot on dji mavic 3.

Aus diesem Text hat Midjourney vier Bilder generiert:

Optisch ansprechende Resultate, aber sie entsprechen nicht meiner Intention. Also habe ich die KI zur Hilfe gezogen und habe Copilot von Microsoft (vielen Dank Jannik für die Einführung) gebeten, aus meinem Text eine ausführlichere Variante mit zehn Sätzen zu formulieren. Heraus kam folgender Text:

The photograph is an overview of an old bus station taken from outside the bus. The station is located in an industrial area and the photograph was taken at night. The photograph has a cold color palette except for the inside of the bus where the woman is sitting. The woman has black hair and a sad expression on her face. She is sitting in one of the buses and looking out of the window. The window has water droplets on it, which adds to the melancholic mood of the photograph. The photograph is taken from a drone using a DJI Mavic 3. The photograph is ultra-realistic and looks like a painting by Edward Hopper. The photograph captures the whole bus and other buses in the background. The photograph is a stunning example of how a photograph can capture the mood of a place and the emotions of a person.

Mit diesem Beschrieb hat Midjourney neue, andere Bilder generiert:

Ich habe noch einmal einen Anlauf genommen:

The photograph is an overview of an old bus station taken from an aerial perspective. There are five busses in the busstation which is located in an industrial area and the photograph was taken at a rainy night. All buses are empty, except one bus in which a lady is sitting inside the bus. The photograph has a cold color palette except for the inside of the one bus where the woman is sitting and looking out of the window. The window has water droplets on it, which adds to the melancholic mood of the photograph. In this one bus, a warm light enlights the inside of the bus. The woman has black hair and a sad expression on her face. The photograph is taken from a drone using a DJI Mavic 3. The photograph is ultra-realistic andhas a style like an Edward Hopper painting.

Nun kam die Busstation besser raus, aber die Szene war von so weit weg dargestellt, dass die einzelne Person nicht mehr sichtbar ist:

Ich habe den Gedanken der Luftaufnahme aufgegeben und zusammen mit Copilot einen neuen Text formuliert:

The photograph is an ultra-photorealistic image captured with a Leica M camera and a 21mm lens. The photograph is a strong wide-angle shot that captures the entire bus station. In the foreground, you can see a bus that is illuminated from the inside. A young woman with black hair is sitting at a window in the middle of the bus, looking sadly out of the window. The photograph was taken during the blue hour, which gives the photograph a cool color palette. However, the interior of the bus where the woman is sitting is bathed in warm light, creating a stark contrast with the cool colors outside. In the background, you can see other buses parked in the bus station. They are all empty, and no other person can be seen in the whole picture except for the one woman sitting in the illuminated bus. It is raining, and you can see drops of water on the windows of the buses.

Hier das neue Resultat:

Immer noch nicht, was ich mir vorgestellt habe vor meinem inneren Auge, aber besser. Das Bild unten rechts hat mir am besten gefallen, und ich habe in Midjourney vier Varianten dieses Fotos generieren lassen:

Wirklich gelungen ist mir die Umsetzung dessen, was ich vor meinem inneren Auge hatte nicht. Das Bild unten trifft zumindest die Stimmung, die ich mir vorstellte, einigermassen:

Nachtrag

Gerade ist Midjourney upgedatet worden, und Version 6.0 ist jetzt online. Mit dieser Version ist es mir zum ersten Mal gelungen, ein Bild zu generieren, das viel näher an meinem Textbeschrieb ist. Vor allem ist jetzt vom System korrekt erfasst worden, dass das Bild von ausserhalb des Busses realisiert worden ist. Die Technologie macht rasante Fortschritte, und in wenigen Monaten werden wir noch akkuratere Resultate sehen.


 
Zurück
Zurück

Schaffhuuse zeigt Herz

Weiter
Weiter

Der Papst und der Dalai Lama beim Kaffeetrinken ...