Doesn't draw what I wanted in Adobe Firefly

@droopydog500 

Thanks for your explanation. Beardless instead of no beard I must use.
It will save a lot of confusion.

The link Writing effective prompts. is what I will study next.
Thanks

I recommend reading this page: Writing effective prompts.

I will highlight a few things...

Your prompt reads like a story. Firefly's model has a hard time unpacking something conversational like that. You should be more succinct and remember that the further left a concept is, the more prominent it will be in the image. Eliminate all words not needed.

I am not sure what you mean by "A drawing of a chef appears".  The model does not seem to have temporal understanding and I am not sure what you were trying to create with that phrase.

It does not really understand verb commands like "create" (as other services do). Start the prompt with a noun phrase which should be the most prominent object.

You have "no beard" and "no moustache" in your prompt. When you want to include "negative" concepts in a prompt, consider this: the model does not seem to understand the coupling of two words where one word negates the other. Because of that, you end up with the thing you are trying to eliminate actually getting added.  For example,

• "no mountain" ends up generating mountains
• "without facial hair" ends up showing beards
• "no men" ends up adding men
• "no stairs" ends up adding a staircase

It is best to try to describe the negative prompt concept in a single word, if possible (even if the word you use is not a real English word):

• "beardless" rather than "without facial hair"
• "mountainless" rather than "no mountains"
• "flat-land" rather than "no mountains"
• "women" rather than "no men"
• "stairless" rather than "no stairs"

Hyphenating words seems to connect words more than a space, but not as much as if it was a single word (if that makes sense). If two words is a "zero" connexion and one word is a "ten" connexion, hyphenating seems to be around "three" in my experience (if that makes sense). But hyphenating does not seem to solve the negative word coupling issue ("no-mountains" is not better than "no mountains").

If you have too many concepts for the model to deliver what you want in one image, consider breaking up the concepts and adding something with generative fill after creating the initial image in text to image.

These are from my learnings over the first year of using Firefly.  I hope they are useful.