Skip to main content
T
TheJamLab
Inspiring
June 23, 2025
Answered

AI does not comprehend Kokopelli - request addition to model library

  • June 23, 2025
  • 1 reply
  • 1028 views

I'm trying to utilize kokopelli art within a text to image prompt. I have added a simple example kokopelli image but the results are nothing like the classic Hopi Native American forms. The prompt indicates that kokopelli is misspelled, so this common art object seems to be absent from the data set.

 

How to get past this and stop wasting credits?

 

Correct answer TheJamLab

I stopped using the term kokopelli and the results are interesting but no where close to my goal. I will pause my account and try again with the next revision. The AI ignores my request for a trio often. For now I will generate some interesting backgrounds (pyramids, UFOs, planets in the sky) and photoshop my existing trio onto those cool environments. I was attempting to have highly detailed and psydellic kokopelli playing realistic instruments. I have no doubt AI will one day get very close to what is intended. Not knowing that a trio has only three players is a WOW failure for sure. Thanks for the suggestions everyone. Peace!


Success!!! The latest "Flash module" solved the Kokopelli problem in an excellent way. Now, I have three detailed Kokopelli musicians that I can import as layers on a Firefly generated background via Photoshop. I was impressed enough to purchase Premiere/Photoshop Elements 2025 as an upgrade from 2022 for $129. I can now create my media campaign for my band! I look forward to Firefly eventually turn my images into videos. Well done Adobe in spite of the fact that I must edit the final products rather then AI being turnkey. This is a great start and I hope the sucess continues.

1 reply

O
Community Expert
Oh.N8Community Expert
Community Expert
June 23, 2025

Thanks @TheJamLab  for sharing this. 

This has to be frustrating. Could you share a screenshot(s) of what you are looking to create? & screenshots of the results?

This would help.

thanks

Nate

T
TheJamLabAuthor
Inspiring
June 23, 2025

Kevin Stohlmeyer
Community Expert
Kevin StohlmeyerCommunity Expert
Community Expert
July 11, 2025
@TheJamLab  schrieb:

 

AI is suppoed to learn and expand with the user base. It should be like exercise. The more it is used the power is increased.

 

Learning doesn't work like that. At least not for Firefly. You can not show it an image and then it will put that into the database and from now on "knows" what you told it.


Hey @TheJamLab two things to note - 1. As @Monika Gause pointed out Firefly does not train on your image inputs. It's learning model is based on licensed Adobe Stock and other approved sources. Knowing Stock is a source, searching the site only shows 1,144 images of Kokopelli so that is a tiny data source. Firefly just doesnt understand the word. 

HOWEVER - the other thing working against you is you are trying to create a Photo generation based on art instead of art. Whenever you do that you are leaving a lot up to interpretation from the AI model. 

 

You can see below, taking your reference image and using "Illustration of native art" gives me something closer to your original image. 

If I change my prompt to something simiar to what you mentioned above with "character drumming with dreadlock hair" and switch to photo content - this is what I get. 

My point is if you remove "Kokopelli" and use your image as a reference with descriptive prompts, you may get closer to what you are envisioning instead of letting the AI interpret what you want. 

 

Terms & ConditionsAccessibility statement
Using the community Terms of use Privacy Cookie preferences Do not sell or share my personal information ad choicesAdChoices