Sunday, 21 June 2026

THE PRINTERS PLANET -- TAOS 2026

I went to THE PRINTERS PLANET in Taos on June 20, 2026:


The Space Cat
could not resist licking it's fishbowl helmet


The Vendors Market ended
when the main tent blew over after 4 PM


Posted by at No comments:

June 19, 2026 -- PORTRAIT

The portrait session on Friday nights is free -- FRIDAY NIGHT FACES -- but the artists had to give their drawings to the sitter:






PREVIOUS PORTRAITS
Posted by at No comments:

Friday, 19 June 2026

MIDJOURNEY Version Variations

I finally got access to MIDJOURNEY'S new "v 8.1" model, which is now the default model since June 11, 2026.  

I decided to do a test, by altering a photo of an ALEBRIJE sculpture in Albuquerque with ALL the model versions of MIDJOURNEY:

ORIGINAL IMAGE
to be altered

The ORIGINAL image I altered
in all the versions of Midjourney

The "v 8.1" loses a lot of spatial clarity -- so I prefer the older "v 7" and "v 6" models.



MIDJOURNEY VERSIONS
"v 8.1" back to "v 3"

Results from Models "v 8.1" down to "v 3,"
going backwards in time

NOTE:  I used my Midjourney Moodboard -- "EZ ART#6" (--profile z9nizie) -- to generate the images in versions "v 8.1" through "v 6.1."

"EZ ART#6" Moodboard
(--profile z9nizie)

*****

v 8.1
(June 11, 2026)

Midjourney prompt:
"Low rider passing the Alebrije sculpture --profile z9nizie"

Animation of "v 8.1" variations



v 7
(June 17, 2025)

Midjourney prompt:
"Low rider passing the Alebrije sculpture --profile z9nizie"

Animation of "v 7" variations



v 6.1 
(July 30, 2024)

Midjourney prompt:
"Low rider passing the Alebrije sculpture --profile z9nizie"

Animation of "v 6.1" variations



v 6
(December 21, 2023)


Animation of "v 6" variations




v 5.2
(June 22, 2023)



Animation of "v 5.2" variations



v 5.1
(May 3, 2023)


Animation of "v 5.1" variations



v 5


Animation of "v 5" variations



v 4
(November 5, 2022)


Animation of "v 4" variations




v 3 
(July 25, 2022)


Animation of "v 3" variations



CONCLUSION

I prefer the older MIDJOURNEY model versions, as the new "v 8.1" model loses a lot of architectural space.

My favorite images below have a lot of SPATIAL qualities, and were generated with previous "v 6" and "v 7" versions.

I re-processed the "v 8" version with the "v 7" model below -- and the result gained more spatial clarity: 

"v 8" version on the left
reprocessed with the "v 7" model on the right


BEST IMAGES
 from PREVIOUS MODEL Versions

More -- EZ AI ART
AI IMAGES 2024 -- Midjourney Landscapes -- Part 1
"v 6" image from January 2024

More January AI
"v 7" from January, 2025


SURREAL AI Slop
"v7" from March, 2026

Also MIDJOURNEY pushes too hard to get me to "train" their model on my personal tastes.  However I have been avoiding this because I am afraid that Midjourney will "OVERFIT" to my tastes, and start generating the same image or flavor no matter what kind of input.  I don't want to generate inbred images.

Midjourney pushes too hard
to get me to declare my preferences

Furthermore, I feel like Midjourney is pushing me, and everyone else, into a particular kind of aesthetic, one that they have determined is the best. I have commented on this since back in 2022. Midjourney wants to become the arbitrator of good taste.  

The latest "v 8.1" model seems to shoehorn us into a kinda Kate Moss heroin chic aesthetic. The previous models championed more of a Moebius aesthetic, which I am more aligned with (they definitely trained on Moebius since his name was amongst those in the background on their front splash page). Before that, the early Midjourney models seemed to have a Tim Burton aesthetic.  I want a "KRRRL" aesthetic.

Perhaps an even more substantial approach would be to get the AI to generate something I could not imagine.  I concur with Brian Eno (in a video that is no longer on YouTube)  -- that would be against Midjourney's nature:

"..so the thing becomes an exercise in trying to force the system to do something that is actually against its nature...because it's nature (ie AI) is to suck up and take the most probable next word...no...I WANT THE LEAST PROBABLE NEXT WORD..."

Lastly I would say that Midjourney does not do a good job generating organic images.  This is probably partially on purpose, to avoid generating porn.  However their censorship is a little over zealous.  And organic forms are really the backbone of art throughout history (I guess Midjourney does not believe that "Man is the Measure.)"

Moreover Midjourney is no longer good in generating images with "space."  The previous models -- "v7" "v6.1" and "v6" did a decent job, but the current model "v8.1" does not, generating fuzzier images.



KREA IMAGES

Last month KREA came out with their own answer to the Midjourney aesthetic with their KREA2 model.  It took me a while to figure out KREA's Moodboards, but eventually I did and generated some styles and images I liked:

KREA 2

ROPE CRITTERS

CLAYTON, New Mexico


Ultimately I think one has to Train models on their own images -- in my case, on my drawings -- in order to get their personal style and unique aesthetic.


MIDJOURNEY MEDICAL

Midjourney went off in a completely different direction, and is now making body scanner hardware:


Maybe Midjourney is worried that FLOW and ChatGPT are going to dominate the image generating scene in the future, so they are branching out.

Posted by at No comments:
Subscribe to: Posts (Atom)