Playing arround with Sketchup diffusion

[rv1974]

@rich o brien said:

@jo-ke said:

In the End: I get the best results with renderings. Here: Twinmotion

Rolling up your sleeves and getting your hands dirty still looks best. Diffusion can help you in terms of direction to take with lighting and colour palette. But for a final result I still believe you need human creativity.

But AI will get there and it will be interesting to see how the likes of Vray, D5, TwinMotion etc respond.

These shots are though. Really nice output.

Meanwhile Chaos implemented DLSS 3.5 thing in Vantage - and it it really makes wonders

[Rich O Brien]

@rv1974 said:

What are benefits of Comfy (in comparison to A1111)?

Its node based so its easier to follow logic if your comfortable in node based environments.

If not stick with A1111.

[jo-ke]

@l i am said:

I find it interesting that the sketchup dufusion and stable diffusion gave a very similar treatment to both images. For instance the sky is almost identical as is the lighting. The only difference I can see is the material mapping and roughness. I wonder why this is?

The Sketchup Diffusion Output is the Stable diffusion input. That is the reason both look similar but stable diffusion img2img devellops it a bit further to a better result.

[rv1974]

interesting observation on AI:

[jo-ke]

overlay in photoshop:
-sketchtup
-skectchupdiffusion
-rayscaper

nice result

---

[pixelcruncher]

@jo-ke said:

overlay in photoshop:
-sketchtup
-skectchupdiffusion
-rayscaper

nice result

Really nice! (I’m sorry, I accidentally downvoted, the buttons are too small for my thick thumbs).

[jo-ke]

further development in stable diffusion

sketchupdiffusion

[jo-ke]

I am using sketchup diffusion to build textures of buildings.

At first I am looking for sketches of fassades.

then I import it to Sketchup, define the colors in the promt and render it.

then I project the texture on my object and model the rest.

This is very fast and effective.

[jo-ke]

a funny weekend project.

some years ago, I was 3D scanned and they made a small 3D Modell of my body.

I scaned the small figure in3D and made a Sketchup modell of it.

The I renderd it in Sketchup diffusion and put it in stable diffusion img2img.
upscaling with my Lora and a reActor Faceswap.

nice result....

su view:

su diffusion:

stable diffusion:

[jo-ke]

quick tutorial to show how I use Sketchup Diffusion:

At first look for a drawing of a building, then texture a cube with it, and set the view to front view. then start Sketchup Diffusion. I typed for promt: "fassade of an old building, dirty beige sandstone" and hit "generate".

then I took the best one and hit "add scene". then I took the sketchup function "project texture" to exchange the drawing with the AI texture.

the cube is textured

some work on geometrie.... finished in less then 5 minutes....

and a quick render in Twilight Render

[jo-ke]

playing some more.

again the 3D figures...

su view

sketchup diffusion to stablediffusion, lora and ReActor Faceswap

not to bad

[jo-ke]

new playing arround:

at first I asked Midjourney to create a unique seamless texture for a modern building

then I created a scene in SU and hit render in Sketchup diffusion.

result was a nice AI render of the scene

then I took the render to kreaAI and a little postpro in Photoshop

[jo-ke]

but a solid render with twinmotion is still better!

and retouched with KreaAI

[jo-ke]

I am still trying to make the best out of sketchup diffusion.
I hope they will develop it further....

When merging su and su diffusion the result comes out quite nice....

su view:

su diffusion:

merged them both in photoshop "hard light"

background enhancment with kreaAI:

[jo-ke]

just 5 clicks and 2 minutes work to produce a nightshot:

[Rich O Brien]

@jo-ke I gotta admit I'm not a fan of AI. I know there's no escaping it. I just find it hard to say wow or well done.

I don't know what to say. Its a timesaver.

[jo-ke]

new try.

I took a picture of my fathers car of the 60ties. and ran it through meshy.ai to get a sketchup- model of it.

then I rendered it with sketchup diffusion and modification in krea.ai, merged and little correction in Photoshop.

everything took less then 10 minutes.

[Rich O Brien]

@jo-ke I never know what to say about AI images...

Its impressive at what it does.

[jo-ke]

I am trying something new.

I tried to use chatGPT to render and it worked quite well.

I took a sketchup Image to chat GPT and used the promt: "render this base image without changing any detail or moving features etc. Ultra realistic with neutral light"

source:

result:

some minor issues but much better than Sketchup diffusion.
I hope Sketchup Diffsion will be develloped further

another one with a cabinet:

source:

result:

[jo-ke]

another try with midjourney wasn't as good as ChatGPT

to many changes in geometry. Still one of the main issues in AI.
this one was the best out of 12 results