Firefly creates movements I did not prompt.

 Hi Kerry5D04,
Thanks for sharing your experience and bringing your questions to us.
 

I understand how frustrating it can be when the results don’t match what you had in mind, but that’s part of the learning curve with generative AI.
Firefly interprets prompts creatively, so the more precise and detailed you are, the closer the output will be to your vision.
 

Here are a few tips that often help:

• Be explicit: Don’t assume the AI will preserve elements automatically. Spell out what should stay unchanged.

• Avoid negative prompting: Instead of saying “no frame, no zoom,” describe exactly what you do want.

• Choose the right model: Some models handle visual effects better than others. (in this case I chose GPT Image 2)

• Use detailed phrasing: For example, “The hand holding the beer is slightly raised in the air, making a partying gesture. All other elements are kept completely preserved.”
   

  

   

If the output still feels off, you can submit feedback directly by clicking the thumbs‑down icon when hovering over the result. That feedback goes straight to the team to help improve Firefly’s behavior.

Let us know if this was helpful, or if you have any other questions.

Hajar