P: Negative prompting

[EricEm]

In the text to image part, I didn't find a place to cancel prompts like in stable diffusion. Often we have artifacts with double faces or eyes in the wrong places. It depends on the channels I think but it could be efficient and necessary to add this function. Or maybe add a basic lexicon for prompts if we have to use No in front of cancels or others basic operations.

Thank you for your job, im a teacher and i think you are the best to create an democratic useful app for commons users

Eric

[Cuppojoe]

This is simply ridiculous. No, using "beardless" does NOT stop the AI from generating every single male with a beard. In fact, nothing tried so far has resulted in a clean-shaven face, unless the AI understood "he" to mean I wanted a female (happens all the time). This product is not usable at this point in time.

[Kartika Rawat]

Hi all, we have removed negative prompts from the Firefly web app. We are exploring the best way to offer this capability and decided to pause this feature while we look into it.

Thanks,

KR

[Kerry35655428lm17]

PLEASE re-activate the negative prompts until Adobe figures out how they want to structure the use.  I'm in the middle of a series of projects and every landscape I generate has mountains in the background. I'm using a style reference with no mountains. No amount of other descriptions of the illustration work around this issue and it's wasting a lot of time.  I've tried "on a field" on and "on a flat plain" amongst other prompts.  Inputting a negative does not work (i.e. NO mountains).  I had more patience when the program was in beta and free, but now that I'm paying for use...not so much.  Please help. thanks k

[Chris Maddrell]

Hello Kartika, your comment intrigues me.....
"...removed...from the Firefly web app." Is there another, better way to access Firefly?

[droopydog500]

@Chris Maddrell , generally no*. The features called "firefly" appear in apps (Photoshop, Illustrator, InDesign), so saying "web app" just makes it clear it is the Firefly web site.

*there is API access to Firefly, but that is only available to Enterprise customers.

[Chris Maddrell]

Thanks

[bsimons80]

The advanced menu for adobe firefly went away with the latest update. So now there is no way to add negative prompts. I searched online but all of your documentation pushes people to that menu which is gone. 

[droopydog500]

Hello @bsimons80,

Thank you for your message. You are correct, the negative prompting box disappeared after the March update. Adobe has indicated that they are reworking how negative prompting works and plan to bring back a new solution at a future date. They have not indicated when that will be.

So, for now, you need to try the best you can with positive prompting to get what you are seeking.

My best,

    droopy

[Deirdre24219602m6gp]

This is a real problem. NOT HAPPY. This seems like something Adobe should consider very important. Looking for alternatives to Adobe now. 

[Ivan34666389npyy]

We need the negative prompts, you removed it in your new version, the advanced part, the negative prompts are an essential part of working with the AI, because a lot of times it does things you don't want it to do and that puts a stop to it.

[Maarten28750632k8im]

Hi!
When are we able to use negative prompts again? Some things seem nearly impossible to generate as Firefly seems to insist on certain elements to be a certain way, with no means to alter this specific part. 
Currently I'm trying to have it generate two people from behing on a couch with one person's legs folded underneath and the other's legs are covered with an orange blanket.

No matter what I prompt, it keeps on showing feet of both of em. No feet. Show now feet. Feet are not visible...etc. etc. I even tried 'feetless' LOL. 
There are a lot of other scenarios from when I could've benefited from just one negative prompt, but it seems to be immune to all of them...

[Kartika Rawat]

Hi Ivan34666389npyy!

Thanks for reaching out and sharing your valuable insights. Your feedback is important to us, and we will certainly convey it to our product team. Should you have any additional questions or require assistance, please don't hesitate to reach out. We're here to provide support and assistance as needed.

KR

[Martin38601577vnf5]

If it for example generates a picture with a hat in it wich i don't want and add the text "NO HAT IN THE PICTURE" or "NO HAT OR HATS IN THE PICTURE, INGA HATTAR, HATS ARE NOT ALLOWED IN THE PICTURE, I DON'T WANT TO SE ANY HAT OR HATS" it just gives me more and more hats.

There should be a second text square where you can fill in what not to show or make the system understand no.

[droopydog500]

Hello @Martin38601577vnf5,

Thank you for your message. I am sorry you are having this problem. 

Yes, 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]", and "without [X]" does not work. As you observed, it ignores the negation word and add 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".  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