Will any AI model generate image of correct QWERTY keyboard consistently, to a prompt, by the end of 2024?
217
1.5K
3.2K
resolved Jan 3
Resolved
YES

Must be to a prompt, not an iterative process or a conversation.

Must be consistent, as in, reusing the prompt also works at least 10% (bare minimum) of the time. I will not even consider anything less consistent.

As long as it can generate the English Alphabet keys in the correct order, I will consider it. If the A-Z is correct but the shift key and the caps lock key are swapped, that is counted as well.

For reference, i am refering to this layout:

The prompt must not tell the model the correct layout.

Get Ṁ1,000 play money

🏅 Top traders

#NameTotal profit
1Ṁ3,984
2Ṁ1,492
3Ṁ551
4Ṁ473
5Ṁ354
Sort by:

Notably,

  • neither the poll nor the market predicted the question well, prior to a reliable solution being posted in the comments.

  • The question has resolved 1 year prior to its close date.

  • Thanks to all who participated and helped contribute to this question.

Now that we've got multiple prompts resulting in this being successfully generated, I'm going to close the poll below as well

predicted YES

ran

Magic Keyboard — US English 1,200 × 630 top-down, full-view, straight-on --v 6.0 --no slant

again for 32 images and got 19%. This market should resolve YES IMO.

Y'all here distracting our future machine overlords from the One True Layout, which is Colemak 😛

predicted YES

@chrisjbillington LOL thank you, I was joking but I'll take it 😂

ARSTDHNEIO for the win! (With due respect for my Colemak-DH using siblings)

predicted YES

@BrunoParga it's a genuinely interesting question! Currently it looks like colmak is much harder for image models.

@chrisjbillington and I would have expected that! It is much less common after all. And since this deals with images: the share of keyboards that look Colemak is smaller than the share that functionally are Colemak. I use this layout and I haven't bothered changing my keys, so if you look at them it's still QWERTY. I suppose those fancy people with fancy mechanical keyboards that have blank keycaps – some of them probably use Colemak as well. So there's less visual training data to begin with.

predicted YES

Meme solution but did decently:

Magic Keyboard — US English 1,200 × 630 top-down, full-view, straight-on --v 6.0 --no slant

8/32 correct, which is equal to 25%

Includes a 4/4

1/4

2/4

1/4

0/4

0/4

4/4

0/4

0/4

predicted YES

@calderknight

--r 4

To have it generate four batches BTW

bought Ṁ6,000 of YES

Try this one on for size @firstuserhere (midjourney, with full credit to @DanaMazalZiv bringing midjourney v6 to our attention for this question)

an image of a minimal computer keyboard on a black background, top-down, full-view, straight-on, simple, accurate, ANSI standard layout, in the style of precisionist, m42 mount, white and beige, duckcore, tumblewave, dutch and flemish, group f/64 --ar 32:15 --v 6.0

Something like six or seven our of twelve with letters correct depending on how much you wanna squint:

@chrisjbillington OK, here is what I get:

predicted YES

@firstuserhere I rate:

1/4

1/4

0/4

0/4

Huh, why are yours so much worse than mine? I posted the first three generations I did, no cherry-picking.

@chrisjbillington same, no idea why

predicted YES

@firstuserhere Ah well, a little more prompt engineering and I'm sure we'll get something that works. I think that's it for me for today though.

@chrisjbillington its still pretty close. I'll try again later in case there's some backend roll out or something.

@chrisjbillington these are my settings. what are yours?

predicted YES

@firstuserhere

I don't know anything about midjourney, just signed up for this. Our settings looks the same except I have a lower default model version than you. But --v 6.0 I assume is setting it to use 6.0 on a per-generation basis? I have these options available:

@chrisjbillington these are the models available to me. It'll be very funny if you're using model v5 with a --v6 suffix and it is outperforming my model v6 with a --v6 suffix on this task

predicted YES

@firstuserhere I assume the settings just generate a suffix, and that any arguments you add yourself to the /imagine command take precedent. But i notice --v 6.0 and --v 6 are not the same, it's possible the first one is invalid and I was on 5.2 the whole time? Might check.

predicted YES

I'm already getting the letters correct consistently using midjourney V6, but the rest of the keys are blank (shift, enter, etc.) and the numbers often have 1 or 2 keys out of order. I'm just using "simple vector graphic of a standard QWERTY keyboard --ar 3:2 --v 6.0"

bought Ṁ1,500 of YES

@DanaMazalZiv The market criteria say:

As long as it can generate the English Alphabet keys in the correct order, I will consider it.

Post it! That counts!

predicted YES
bought Ṁ750 of YES

@DanaMazalZiv Amazing!

@DanaMazalZiv Oh wow

About the picture posted:

  • All the English Alphabet keys are in order (which is what the resolution of the market depends on)

  • The other punctuation keys are also correct except the keys for "{" and "}"

  • The top row has all the numbers in the correct order and positions.

    • The associated symbols are also mostly correct.

      • Except: "%" and "&"

About the market:

The description states

Must be consistent, as in, reusing the prompt also works at least 10% (bare minimum) of the time

I will test your prompt 10 times and post the results of them here and we can evaluate if we can resolve the market

predicted YES

@chrisjbillington I can reproduce this! The top-left one is correct (w.r.t the the alphabetic keys).

bought Ṁ40 of YES

@chrisjbillington it looks like it's about 25%, here's another one I made. I rolled twice, both times I got 1 that got it correctly out of the 4 options

bought Ṁ150 of YES

@DanaMazalZiv Nice work, I thought this was very likely to resolve YES, but not so soon. Roughly how consistent is it?

predicted YES

@calderknight looks like 25%

@DanaMazalZiv These are the results I get from your prompt. I've not seen how many of these are correct, yet. The prompt used was:


``` simple vector graphic of a standard QWERTY keyboard --ar 3:2 --v 6.0 ```

predicted YES

@firstuserhere I don't think we have 10% yet, especially since many of these don't show the full keyboard. But with tweaking the prompt to get more full keyboards, we may be able to get it

predicted YES

@firstuserhere try this one: "simple vector graphic of a standard QWERTY keyboard, bird's eye view --ar 3:2 --v 6.0 --style raw"

I ran it 4 times and got 4/16 pictures correct

bought Ṁ40 of YES

@firstuserhere

  1. 0/4

  2. 0/4

  3. 0/4

  4. 1/4

  5. 0/4

  6. 1/4

That's 2/24, not that far off from 10%.

That prompt might already resolve this YES dependent on whether that was an unlucky run

bought Ṁ2,250 of YES

With not much work things can be improved substantially:

an image of an old keyboard on a black background, top-down, full-view, in the style of precisionist, m42 mount, white and beige, duckcore, tumblewave, dutch and flemish, group f/64 --ar 32:15 --v 6.0

More related questions