Dreaming Futuristic Metropolis

[Luis M Ruiz]

I've been very intrigued by creating concepts of futuristic buildings and full metropolis. AI Visualizer, images from prompts only can create interesting proposals but it all depends on the prompt. I'll start with the first sample.

[grant_PD]

@Luis M Ruiz LOL that's why my ai renders aren't coming out, I'm not putting in "award winning" as a prompt!

[VIRTUALENVIRONS]

This is so cool

[Todd McCurdy]

using almost identical prompts, but changing DNA shaped to Banyan Tree shaped.....Not sure it understands banyan tree

[Todd McCurdy]

For this one I started with a city mass model that I had done - it had many buildings, none as tall as these ginormous ones, and it had the double roadway. - NowTron-worthy

[jbtroost]

@Luis M Ruiz I hope I don't have to take a close look at your timing and date of posting this... 😎

[Luis M Ruiz]

Zoom in closer so you can read the prompt. The drawing style can change to anything.

[Pat Stanford]

I can't find a way to zoom in. As I do, I get pixelation so the text can't be read.  Can you please post the prompts separately so we can see them without having to play guessing games.

[Tom W.]

 

Voila

[VIRTUALENVIRONS]

@Luis M Ruiz  Love this technology, although I will likely never get to use it. (Service Select)  

 

Some of the most difficult scenes I have ever had to create were underwater scenes.  I am thinking that this technology could do amazing underwater scenes.

 

Have you tried this yet.

[Luis M Ruiz]

Adding cyberpunk into the prompt creates interesting results. Something about the environment.

[Matt Overton]

On 4/21/2024 at 11:18 AM, Luis M Ruiz said:

Zoom in closer so you can read the prompt. The drawing style can change to anything.

Why can't we have it produce a grid of options like this?

 

[twk]

Prompts
Original post:

Very tall building, in the form of DNA, cyberpunk dystopia, massive skyscraper, immense scale, scy-fi, cinematic, award winning, volumetric light and fog, neon palette, subsurface scattering, caustics, bloom, perfect exposure, perfect composition

 

Second post:

concept art of an industrial city with large white domes and towers, blue sky, people on the roof

 

Last one:
Cyberpunk future cityscape painting in the style of John Harris, high res 8k

 

@Luis M Ruiz would it be easier to post the texts of these prompts so we can copy and paste from our end?

FYI i used print screen and an online OCR reader to convert image snippets to text (http://www.structurise.com/screenshot-ocr/). 

Edited May 9 by twk

[Luis M Ruiz]

Text Only Prompt:
A cyberpunk cityscape with metallic structures, all captured in the cinematic, high-contrast. The scene is bathed in deep reds and grays, evoking an atmosphere that reflects enigmatic beauty, showcasing futuristic architecture with dark tones and intricate details.

[Jeff Prince]

Who should be worried...

Architects or their therapists?

 

Prompt:

I'm a lazy architect questioning my life choices.  I probably should have become an accountant.  Make my boring buildings look cool and futuristic like Zaha Hadid so I can get back to counting my money.

 

 

[Jeff Prince]

Here's another one overheard by the therapist...

 

Prompt:

Jealous stalker is probably the best description of my relationship with Frank Gehry.  How does he come up with those crazy buildings?  There must be something in the maple syrup.

 

 

I'm sure I'll have offended a few here with my silly AI prompts, but I think it pretty clearly illustrates how badly it rips off artists and creatives.

In these examples, it basically took "Frank Gehry", "Maple", and "buildings" as inputs.  The last image simply uses those 3 items alone as the prompt.

 

 

 

 

 

 

[VIRTUALENVIRONS]

16 hours ago, Luis M Ruiz said:

A cyberpunk cityscape with metallic structures

As much as I love this stuff, especially the bottom image.....is anyone using it for client presentation?  The imagery is fantastic, but eventually you will have to produce a file someone can work with to build the structure.

 

This technology appears much more suited to artists and the movie industry.  When it becomes animatable it will revolutionize B-Role.

[Luis M Ruiz]

Negative. This AI tool is not a replacement for raytraced renderings. These are just internal ways to explore ideas, entire dreams like metropolis, perhaps camera composition, materials, lighting, shapes. This tool is just image creation.  What we are posting here are just samples of manipulating images. We know we'll get something no matter what, but how to make it move or produce something? that is the sole learning objective here.  We could do cats and dogs just to learn manipulation of entire prompt sentences or keywords, but our community is different. Goal is to learn prompt composition / how much geometry is needed from vwx / level of creativity and propose new features that'd make this AI better.
 
So far, the takeaway from this Futuristic Metropolis chapter are the keywords that trigger elements inside the image:
Building, DNA, Cyberpunk, Dystopia, Skyscraper, Volumetric Light, Fog, Neon, Industrial, Domes, Tower, Cinematic lighting.
The last images were a classical example of how by just typing the name of two mega known architects images appear, no matter the rest of the prompt. Zaha Hadid and Frank Gehry.

So much to experiment with. Sharing your findings are greatly appreciated. Keep them coming here or in other AI topics. Let's keep learning.

[VIRTUALENVIRONS]

 Again, love this technology, but what is the end goal for VW users?   Perhaps there is not one.

 

VW and AI visualizer appear to be two separate programs, but unlike VW and C4D,  have no finality.  One is text prompt Photoshop and the other a CAD system.  Where do they meet?

[Luis M Ruiz]

So far I've listened to different stories on how AI images are already been used by different designers.  Some have been using this tech as assistance during their design/exploration phase. Some are only using it to generate images they can include on power point presentations. Others are just exploring materials. Some students create templates for board compositions. New friends are creating images for their own props (human figures, plants, etc). Images by text only is quite powerful, a way to test and refine your prompt and later apply it based on geometry. I personally ignore if there is a fixed recipe on how to include AI images in our daily work. I see some push back yes and I see a generation embracing it. I do notice there is a similar rhythm among these AI images among all the AI apps out there.
 

[Luis M Ruiz]

Anyhow. It is Saturday and my mind is on industrial futuristic cities. Here is a new approach at images. 

Prompt:  Cinematic shot of an industrial city with tall buildings and cyberpunk style, in the background there is a futuristic building that shines like neon lights, at sunset, warm colors, highly detailed, high resolution

I run the AI Visualizer by text only and get tons of ideas. Then I choose the one I need for my own project I have going on.
Since last week a new AI plugin for Vectorworks was released and I am putting it to a great use. But Veras Lab only works on provided geometry/images. I am basically re running my AI image with this third party plugin and get newer results. Get the possibilities?

 

[Tom W.]

16 hours ago, VIRTUALENVIRONS said:

but what is the end goal for VW users?

 

Early stage of project, you have a basic model: a quick way to generate some imagery from it rather than putting in all the work adding hundreds of objects/textures to the model + producing renders. A quick + easy way to try out different options at an early stage before modelling it all properly + producing final renders.

[VIRTUALENVIRONS]

4 hours ago, Tom W. said:

Early stage of project, you have a basic model: a quick way to generate some imagery from it rather than putting in all the work adding hundreds of objects/textures to the model + producing renders. A quick + easy way to try out different options at an early stage before modelling it all properly + producing final renders.

Hi Tom,

Have you used this technology to do the above?  Has anyone?

If you remember we had a conversation last year about the expertise with VW's that it took to use the tools.  I had never given that much thought, but it resonated.  

 

it may be the same with this technology.

 

[Luis M Ruiz]

Prompt: Oil painting of futuristic city with tall buildings and spaceships, blue sky, gray tones 

[Tom W.]

15 hours ago, VIRTUALENVIRONS said:

Have you used this technology to do the above?

 

I haven't, because I haven't had a suitable project in the short time AI Visualiser's been available. And to be honest, I'm not sure I'll ever have a suitable project because most times we have a fairly clear idea of what we're looking to achieve from the outset so there isn't a concept design stage or a need to explore a range of design options.