Jump to content

Dreaming Futuristic Metropolis


Recommended Posts

  • 2 weeks later...
  • 2 weeks later...
Posted (edited)

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

image.thumb.png.a773175e619d41af577f16cbbe522eec.png

 

Second post:

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

image.thumb.png.517827525075be356cf4da59699af8c1.png

 

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

image.thumb.png.0b2c25dabd8f411dbc7552f04773953d.png

 

@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 by twk
  • Like 1
Link to comment
  • Vectorworks, Inc Employee

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.
Screenshot 2024-05-10 at 2.48.09 PM.pngRed cyberpunk cityscape.png

  • Like 2
Link to comment
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.

  • Like 2
Link to comment
  • Vectorworks, Inc Employee

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.

  • Like 1
Link to comment

 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?

Link to comment
  • Vectorworks, Inc Employee

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.
 

  • Like 2
Link to comment
  • Vectorworks, Inc Employee

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?

 

Screenshot 2024-05-11 at 12.45.08 PM.png

Enhanced cityscape.png

  • Like 2
Link to comment
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.

  • Like 1
Link to comment
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.

 

Link to comment
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.

 

 

 

 

  • Like 1
Link to comment

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Reply to this topic...

×   Pasted as rich text.   Restore formatting

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

×
×
  • Create New...