• Global community
    • Language:
      • Deutsch
      • English
      • Español
      • Français
      • Português
  • 日本語コミュニティ
    Dedicated community for Japanese speakers
  • 한국 커뮤니티
    Dedicated community for Korean speakers
Exit
13

Firefly can't count

Explorer ,
Jan 15, 2024 Jan 15, 2024

Copy link to clipboard

Copied

Why can't Firefly count? It's been over a year with hundreds of complaints about how Firefly can't count. Is counting really all that hard?
Another attempt... I typed "eight wheeled car" and EVERY image was a four wheeled car. Over and over again. Firefly couldn't grasp a car with more than four wheels. So, I tried fewer than four. I typed in "one wheeled car" and it gave me four-wheeled cars again.

I tried a different approach. I typed in "eight birds". It gave me six.

Seriously, why can't Firefly count?

Bug Unresolved
TOPICS
Imaging

Views

2.5K

Translate

Translate

Report

Report
Community guidelines
Be kind and respectful, give credit to the original source of content, and search for duplicates before posting. Learn more
community guidelines
32 Comments
Explorer ,
Jan 28, 2024 Jan 28, 2024

Copy link to clipboard

Copied

Just a quick note, Maciej...

You mentioned that it's very rare for people to count items when describing images in text. Do you mean when they are experimenting with firefly or when they are using AI for real world projects?

 

I'd like to point out that the people in this thread who posted examples are those "rare" occurrances you refer to. In other words, I personally don't think it's rare (in my line of work) to ask for precise numbers when creating imagery. I do it constantly.

My client wants a beer ad with three bottles. Classic configuration.

The football coach wants a poster with eleven players (a full team) to inspire his JV team.

The baseball coach wants a poster with nine players (a full team) to do the same.

The dog breeder wants an ad with four dogs.

In my world of photography, graphic design and commercial art, specific quantities are normal.

 

(for what it's worth, I'm not trying to challenge your assertion. I'm merely curious about your perspective and want to know more because it doesn't fit my experiences.)

Votes

Translate

Translate

Report

Report
Community Expert ,
Jan 28, 2024 Jan 28, 2024

Copy link to clipboard

Copied

If you prefer in simple terms. That would be far too expensie and require yet years to gather data and completly new model to include such simple for humans and yet difficult for AI model thing to do. I would estimate a milions of budget and at least 3 years of reserach.

 

I am not sure, @CMass , who marked this as the "correct answer", but it is not.

Votes

Translate

Translate

Report

Report
Explorer ,
Jan 28, 2024 Jan 28, 2024

Copy link to clipboard

Copied

..."I am not sure, @CMass , who marked this as the "correct answer", but it is not."

 

Come on, droopydog500, you can't just leave us hanging... you must know... what is the correct answer? :))

Votes

Translate

Translate

Report

Report
Participant ,
Feb 02, 2024 Feb 02, 2024

Copy link to clipboard

Copied

When having questions about an AI, ask an AI... this is from a long chat I had with Google’s Bard:

 

Me: in my experience, AI has problems counting, both when chatting and when generating images. Why do you think this is?

 

Bard: You're absolutely right! AI image generators do struggle with counting in images compared to humans. There are a few key reasons for this:

  • Data-driven learning: AI models learn from the data they're trained on. While they have huge datasets, representing all possible variations of counting accurately can be difficult. For example, if an AI sees mostly images with 2 apples together, it might struggle to differentiate 3 apples later.
  • Lack of abstract understanding: Humans understand numbers conceptually, but many AI models don't. They see objects as individual shapes and colors, not abstract quantities. This makes it challenging for them to accurately count across different arrangements and contexts.
  • Focus on image generation, not object recognition: Some AI image generators might prioritize creating an aesthetically pleasing image over ensuring precise counting. While they might capture the overall scene well, the exact number of objects might be inaccurate.

 

Here are some additional factors that can contribute to counting issues:

  • Object variations: Size, position, overlapping objects, and other variations can confuse the AI, making it hard to distinguish individual instances.
    Background complexity: Cluttered backgrounds can further complicate the process of isolating and counting objects.
    Limited training data: As mentioned earlier, more diverse and specific training data could improve counting accuracy.
  • Researchers are actively working on improving AI's counting abilities. Techniques like incorporating object recognition modules and using synthetic data with controlled variations are being explored.

 

Overall, while AI has made significant progress in image generation, counting accurately remains a challenge. Understanding the limitations and reasons behind them is crucial for interpreting AI-generated images and using them appropriately.

 

So, the correct answer to “Why can’t Firefly count?” is “Because image generation doesn’t work like that.”

Votes

Translate

Translate

Report

Report
New Here ,
Feb 24, 2024 Feb 24, 2024

Copy link to clipboard

Copied

I am writing prompt for Seven (7) running horses but it's showing 5, 6 but not exact 7 horses.

Votes

Translate

Translate

Report

Report
Community Expert ,
Feb 24, 2024 Feb 24, 2024

Copy link to clipboard

Copied

 

@Anagha35667129plh1 

 

Artificial Intelligence, including Adobe Firefly, does not do well with numbers of items (yet).

 

Jane

 

Votes

Translate

Translate

Report

Report
Community Expert ,
Feb 26, 2024 Feb 26, 2024

Copy link to clipboard

Copied

LATEST

Jane is correct. One way to overcome this is try to get close to the number with more fuzzy terms (such as "many") and then adding/subtracting to get the exact number using generative fill.

Votes

Translate

Translate

Report

Report