My composition reference (logo) isn't being used by Firefly

Hello @evagoethals,

Thank you for your message. 

First, the model does not understand the concept of a word being negated by the word in front of it. So using "not [X]", "no [X]", "exclude [X]", "minimise [X]", "with no [X]", and "without [X]" does not work. It generally ignores the negation word and adds to the image or video the thing you are trying to avoid.  You basically need to find "positive" words and phrases telling the model what you want to see rather than telling it what you do not want to see.  

In this case, I found Model 3 works better than Model 4.  I used these settings:

This prompt:

minimalist, single large unified metallic silver balloon, featuring a thick vertical element with a double-arched base, joined centrally to a sweeping, single S-curve extending to the right, clean black background

And got this:

I did try a number of things that did not work. The reference image looks like the merger of a "K" and "B", I did try using that in prompts but it would not merge them together in the stylised way the composition reference was:

I did have help from Google Gemini. I had a long dialogue with it where I gave it your reference image, the prompt I was using, what I wanted, and what Firefly was generating and I was able to get it to help me refine the prompt to what it is above. I have found that if I cannot figure it out myself, LLMs can help.

My best,
    droopy