Skip to main content
Participant
February 28, 2025
Answered

hat alwaysis on riders head even if say rider with no hat

  • February 28, 2025
  • 1 reply
  • 217 views

i wasted my credits. hat alwaysis on riders head even if say rider with no hat. How can i solve this problem i need a video generated a rider with no hat 

Correct answer droopydog500

Hello @Bestminster,

Thank you for your message. 

Can you please share your prompt and the results. When you mention "rider", I am not sure if you mean bike, bicycle, horse, etc.

 

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]", "with no [X]", and "without [X]" does not work. As you observed, it ignores the negation word and adds to the image 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.  Such as "flat land" rather than "no mountains" or "desolate" rather than "no people" or "bare head".  If I am not sure how to describe something I want to exclude in a positive way, I will ask Google Gemini or ChatGPT for ideas.  Just be aware that when they give prompts, they are usually too wordy and conversational, so you have to edit them, but they are good for ideas.


Thanks,
    droopy

1 reply

droopydog500
Community Manager
droopydog500Community ManagerCorrect answer
Community Manager
February 28, 2025

Hello @Bestminster,

Thank you for your message. 

Can you please share your prompt and the results. When you mention "rider", I am not sure if you mean bike, bicycle, horse, etc.

 

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]", "with no [X]", and "without [X]" does not work. As you observed, it ignores the negation word and adds to the image 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.  Such as "flat land" rather than "no mountains" or "desolate" rather than "no people" or "bare head".  If I am not sure how to describe something I want to exclude in a positive way, I will ask Google Gemini or ChatGPT for ideas.  Just be aware that when they give prompts, they are usually too wordy and conversational, so you have to edit them, but they are good for ideas.


Thanks,
    droopy

Adobe Community Expert (not an Adobe employee)
Participant
February 28, 2025

Thank you very much . it worked the way you said.  Could you please advise What is the best way to create a longer clips beacuse it was said 70 seconds  when i subscribed, but now is only 5 seconds... ( 

Thanks a lot in advance 

droopydog500
Community Manager
Community Manager
February 28, 2025

Hi @Bestminster,

 

You can only generate 5 seconds in a generation.  To generate longer clips, you can take the last frame of a five second clip and use it as the keyframe for the next generation. You can keep doing this as many times as you want and use a video editing tool to assemble those five second clips into one longer video.

 

My best,

    droopy

Adobe Community Expert (not an Adobe employee)