2024 Porsche 914?, Dall-E designed Options

[technicalninja]

Really nice illustrations!

The background would be harder to complete than the car.

OH, please, please ask it for an updated 916...

[trylon]

Really nice illustrations!

The background would be harder to complete than the car.

OH, please, please ask it for an updated 916...

As requested:

[technicalninja]

that's 904...

Way cool.

Not 916. It doesn't know what a 916 looks like and it probably looked as close as it could and came up with 917...

Still look likes bad-assed 904s

[trylon]

that's 904...

Way cool.

Not 916. It doesn't know what a 916 looks like and it probably looked as close as it could and came up with 917...

Still look likes bad-assed 904s

Yes, requested 916 and got those.

[technicalninja]

I introduced my dad to the thread today.

He was blown away!

We will use AI in his designs from now on.

Not in the vehicles, in the back grounds.

The background work is as cool as the cars and FREAKING HARD TO DO by an artist.

His backgrounds will be AI now...

Thanks for sharing!

It was very interesting and entertaining.

The miss-designed 904s were very telling as well.

It would be nice to feed it an image to start from.

[trylon]

I introduced my dad to the thread today.

He was blown away!

We will use AI in his designs from now on.

Not in the vehicles, in the back grounds.

The background work is as cool as the cars and FREAKING HARD TO DO by an artist.

His backgrounds will be AI now...

Thanks for sharing!

It was very interesting and entertaining.

The miss-designed 904s were very telling as well.

It would be nice to feed it an image to start from.

Ha! Simultaneously encouraging and damning. Thanks for sharing his response.

[Cairo94507]

OMG! I love that 904 rendering! (IMG:style_emoticons/default/beerchug.gif)

[Jack Standz]

Very nice renderings!

It's amazing what AI can do with these designs. But, why can't AI spell Porsche correctly? (IMG:style_emoticons/default/smile.gif) (check out the orange car above, and the car & building in post #38)

[technicalninja]

Very nice renderings!

It's amazing what AI can do with these designs. But, why can't AI spell Porsche correctly? (IMG:style_emoticons/default/smile.gif) (check out the orange car above, and the car & building in post #38)

You're right!

It has misspelled Porsche a couple of different ways.
Wonder if it's a copyright thing. Probably is.

Use Ferrari in any published advertising without Ferrari's approval...

Just make a copy of an old Ferrari and they will visit, even if you call it something else.

I noticed the seats are not well rendered but look at the road surface in the orange 904 illustration. Freaking perfect! So hard to get both the shiny asphalt look and then the reflection of the car.
Very realist IMO.

[trylon]

If you are not familiar with the technology, it might be difficult to understand the errors that Dall-E produces.

Here’s what Chat has to say about it:

In DALL-E generated images, words or text elements may appear misspelled or jumbled for several reasons:

1. **Training Data Limitations**: DALL-E is trained on a vast dataset of images, but this dataset may not have sufficient examples of all words spelled correctly within images. As a result, the model might not learn the correct spelling for every word.

2. **Text Representation Challenges**: AI models like DALL-E are primarily designed for visual generation, not textual accuracy. The model might struggle with representing text accurately within an image, especially if the text is a secondary element in the image.

3. **Context Understanding**: DALL-E interprets text prompts and generates images based on them. However, its understanding of context and nuance, especially when it comes to text within images, might be imperfect. This can lead to misspellings or contextually incorrect text.

4. **Model Constraints**: The current state of AI technology, while advanced, still has limitations. Accurately generating text within images remains a challenging task due to the complexity and variability of written language.

5. **Image and Text Fusion Complexity**: Combining visual and textual elements seamlessly is a complex task. The model may excel at creating visual representations but falter when it comes to integrating text naturally and accurately.

6. **Randomness in Image Generation**: Part of the image generation process involves a degree of randomness. This can sometimes result in unexpected or inaccurate details, including text.

These reasons highlight the challenges faced in the intersection of visual and textual AI generation. As AI technology continues to evolve, improvements in these areas are likely to occur.

[flat4guy]

These are all good looking cars - I would drive any one of them

[wonkipop]

from a critical artistic and technological point of view of view what is called AI is not intelligence.

for one reason. it is impossible for it to be original.

its merely recombining the past (stuff that already exists).

which is what all these images are.
this is what happened to architectural design in the 1980s.
it was called post modernism.

@JeffBowlsby knows what i mean.


--------

to get this into perspective.
it would be impossible for AI to conceive of the APOLLO project to land on the moon.
the entire apollo project was original.
never done before. there were no images to remix and reconfigure.
the APOLLO moon landing is the proof of just how powerful the human brain is.

mind you i am not discounting the idea there could truly be AI in the future.
but this gentleman is not it.

this is AS ----- >ARTIFICIAL STOOPIDITY.
check the view through the windscreen of these renderings.
the far side of the car in all the renderings does not match the visible near side.
there is a fricken quarter window behind the door. (IMG:style_emoticons/default/biggrin.gif) (IMG:style_emoticons/default/biggrin.gif) (IMG:style_emoticons/default/biggrin.gif) (IMG:style_emoticons/default/beer.gif)

onwards into the future which has not arrived yet.
except in 1969 when the 914 was launched and looked original.
and neil armstrong planted his original design moonboot in the moon dust while wearing his original design moon suit having steered his original design moon vehicle down on to the surface. a new problem begats originality as a solution every time.
lets see if this BS version of AI could deliver those kinds of answers.

(IMG:style_emoticons/default/beerchug.gif)

[Front yard mechanic]

I like the quarter window on one side. that way my yappy dog can stick his head out

[mate914]

If you are not familiar with the technology, it might be difficult to understand the errors that Dall-E produces.

Here’s what Chat has to say about it:

In DALL-E generated images, words or text elements may appear misspelled or jumbled for several reasons:

1. **Training Data Limitations**: DALL-E is trained on a vast dataset of images, but this dataset may not have sufficient examples of all words spelled correctly within images. As a result, the model might not learn the correct spelling for every word.

2. **Text Representation Challenges**: AI models like DALL-E are primarily designed for visual generation, not textual accuracy. The model might struggle with representing text accurately within an image, especially if the text is a secondary element in the image.

3. **Context Understanding**: DALL-E interprets text prompts and generates images based on them. However, its understanding of context and nuance, especially when it comes to text within images, might be imperfect. This can lead to misspellings or contextually incorrect text.

4. **Model Constraints**: The current state of AI technology, while advanced, still has limitations. Accurately generating text within images remains a challenging task due to the complexity and variability of written language.

5. **Image and Text Fusion Complexity**: Combining visual and textual elements seamlessly is a complex task. The model may excel at creating visual representations but falter when it comes to integrating text naturally and accurately.

6. **Randomness in Image Generation**: Part of the image generation process involves a degree of randomness. This can sometimes result in unexpected or inaccurate details, including text.

These reasons highlight the challenges faced in the intersection of visual and textual AI generation. As AI technology continues to evolve, improvements in these areas are likely to occur.

It will act like the programmers teach it.
Matt

[mate914]

from a critical artistic and technological point of view of view what is called AI is not intelligence.

for one reason. it is impossible for it to be original.

its merely recombining the past (stuff that already exists).

which is what all these images are.
this is what happened to architectural design in the 1980s.
it was called post modernism.

@JeffBowlsby knows what i mean.


--------

to get this into perspective.
it would be impossible for AI to conceive of the APOLLO project to land on the moon.
the entire apollo project was original.
never done before. there were no images to remix and reconfigure.
the APOLLO moon landing is the proof of just how powerful the human brain is.

mind you i am not discounting the idea there could truly be AI in the future.
but this gentleman is not it.

this is AS ----- >ARTIFICIAL STOOPIDITY.
check the view through the windscreen of these renderings.
the far side of the car in all the renderings does not match the visible near side.
there is a fricken quarter window behind the door. (IMG:style_emoticons/default/biggrin.gif) (IMG:style_emoticons/default/biggrin.gif) (IMG:style_emoticons/default/biggrin.gif) (IMG:style_emoticons/default/beer.gif)

onwards into the future which has not arrived yet.
except in 1969 when the 914 was launched and looked original.
and neil armstrong planted his original design moonboot in the moon dust while wearing his original design moon suit having steered his original design moon vehicle down on to the surface. a new problem begats originality as a solution every time.
lets see if this BS version of AI could deliver those kinds of answers.

(IMG:style_emoticons/default/beerchug.gif)

Sounds about right. It can not produce original design. It can only copy what man has done. Sometimes your wise also...
Matt

[76-914]

They're all gorgeous. I wouldn't kick any of them out of my garage. (IMG:style_emoticons/default/biggrin.gif)

[73-914]

Love this interpretation...





Oh wait. That's mine...

Wait . . . That’s a 914? (IMG:style_emoticons/default/happy11.gif) (IMG:style_emoticons/default/av-943.gif)

(IMG:style_emoticons/default/agree.gif)

[trylon]

Gentleman and Ladies-

Although this is hardly the venue to argue the merits and demerits of Generative Pre-trained Transformers, you are all making interesting points— to each of which there are equally interesting responses.

As a researcher in artificial intelligence since the 80’s (https://www.machineethics.com/) (https://www.researchgate.net/profile/Michael-Anderson-67), let me just say this. The fact that this technology, one that simply guesses the next statistically best response to given input, produces the kind of behavior that these systems do is nothing short of a discovery at least as momentous as that of fire.

[technicalninja]

(IMG:style_emoticons/default/agree.gif)

Significant!
A little disturbing...

[technicalninja]

Even I was sucked in without too much effort.

"We'll just use it for backgrounds..."