Tell us what you think of SketchUp Diffusion! This survey will take approximately 5 minutes of your time and will help ensure that our team remains focused on the things that matter to you. [image] SketchUp Diffusion Labs Customer Feedback Form We would love to hear from you. Your input is incredibly valuable and will help us improve our ability to serve you. Thank you! The SketchUp Team

[image] sagarenarquitectos: when i render some door are turned into windows , the bot changes textures even after prompting to do otherwise, also the tv is turned into a tv , i have a curtain in one wall and in some renders every wall is made out of curtains, You’re asking something that’s hard/too difficult for the current state of SketchUpDiffusion. Interiors can be a challenge for any SD program. In my experience, the AI works best if the objects that it has to ‘calculate’ are 100% in view. If you just have a fragment of a kitchen or a swimming pool, the AI most often has trouble ‘recognizing’ the objects and renders all kind of ‘creative’ solutions You could have a look at other StableDiffusion solutions like ComfyUI or Automatic1111 and use inpainting to have more control over what you like the AI to change/render.

There should be a default setting for just rendering it with the materials and textures and shapes we already made. A large percentage of SketchUp users work in architecture and interior design, and we already know what materials we need to use for projects. We just want to be able to use AI to make them look more realistic since SketchUp itself doesn’t have an included rendering program. I also can’t use diffusion since it turns my cabinets into windows or skews something I modeled to specifically look a certain way. My renderings need to match my construction documents. I literally bring my SketchUp models into chief architect for my construction plans and elevations. The AI renderings don’t match the drawings when spikes are added and cabinet faces and textures change. When the user already knows how to model and apply textures (as is the purpose of SketchUp), then having all these grand AI alternate versions deviate from what the actual artist already created. AI can be useful outside of SketchUp for those who don’t know how to model and apply textures themselves. This isn’t the case for most SketchUp users though. We just want to render the scene we created with AI, and then have potential other creative options. The default option should be our own creation though.

Like all AI I have tried so far it’s a bit like asking a small child genius to create something for you. It’s done with good to sometimes even breathtaking technique but with the understanding, experience and maturity of an infant. I can’t see a serious use for this until it is much maturer.

What you are talking about would be a rendering engine. There are many to choose from in the market already. Diffusion is decidedly not a rendering engine, it’s not calculating light and surfaces or materials, UVs or bumpmaps, it’s not even really looking at the 3D data. It’s just taking 2D shapes from your screen and substituting it’s best guess based on other images it’s seen. It’s really an early stage brainstorming or iteration tool, not a render engine. It’s actually so good at it’s guessing/substitution job that it’s getting pretty close in some cases to what looks like a rendered image. Leading many to get excited at the idea of an “automatic” render engine, I get that, but it’s a far stretch really, as the technology is very different. [image] endlessfix: Perhaps there is some natural confusion about what Diffusion really is. This is not a rendering engine, it does not calculate physical light off of objects in 3Dspace like a rendering engine nor does it create specific materials for any given surface. This is more like a game you play with an alien artist who lives on the moon and watches the earth through a telescope. The AI has some vague ideas about what this planet is and how things work around here, but it doesn’t really know the “why” of what it has observed. You send off a letter (your prompt and input geometry) to the moon and describe a picture and then the artist paints it according to their own ideas and sends it back. The better you describe the painting you want the closer it can get but being an alien and not living in this world it’s also bound to get some fundamental things wrong from time to time. With these expectations, and properly used, diffusion is capable of some extraordinary things.

[image] endlessfix: It’s actually so good at it’s guessing/substitution job that it’s getting pretty close in some cases to what looks like a rendered image That’s because its training data was rendered images, and it learned how to imitate and paste together the kinds of things it saw there. It really has no idea what it is looking at or why it looks that way beyond the words and phrases in the descriptions that went with the training images.

[image] endlessfix: Diffusion is decidedly not a rendering engine, it’s not calculating light and surfaces or materials, UVs or bumpmaps, it’s not even really looking at the 3D data. Perhaps the team’s description is misleading ? viz: [image]About the SketchUp Diffusion category What is SketchUp Diffusion? Diffusion offers a number of options that allow you to define the visual style of the rendered image and control the extent to which either the snapshot of your SketchUp model and/or the text-based prompt, influence the output. Once an image is generated, you can choose to overlay the image atop your SketchUp model and save it as a scene that you can refer back to later, or you have the option to save/download the rendered image.

Every time I render something, it shows the lines of the model. I can’t find a setting to turn this off, although I have found that I can Hide the model, then turn the visibility of the axes off. Is there a way for it to automatically hide the model? Also add my vote for having it respect the materials, or at least the colors, of the model.

I would also like to know what was used to train the AI. I put something out on Facebook, and an artist friend who is concerned about how AI is causing problems for artists because it was “trained” on their work suggested I ask. It makes me super concerned about infringing on someone else’s designs…

[image] KatAdair: I would also like to know what was used to train the AI If you would do a simple search on the forum with “diffusion learning” You would find this: https://help.sketchup.com/en/under-hood This link was even placed earlier in this thread…

I’ve posted a few times. I have all the same thoughts about materials as others. There is something more mild that I think could be addressed. When I add a scene to my image from my diffusion results (ipad) it is labeled “render”, which it is not. This might help alleviate a modicum of confusion. [IMG_2962] And then some images for fun :slight_smile: [IMG_2959] [IMG_2960]

SketchUp Diffusion: Share your Feedback

AI Topics

DanRathbun February 14, 2024, 7:38pm 66

Perhaps the team’s description is misleading ? viz:

Topic		Replies	Views
SketchUp Diffusion Feature Requests AI Topics	74	4803	December 4, 2024
SketchUp Diffusion Gallery AI Topics	51	8011	January 10, 2024
About the AI Topics category AI Topics	23	6977	January 19, 2024
Dificulties with Diffusion AI Topics	16	1601	December 29, 2023
Sketchup Diffusion - basic photorealistic rendering AI Topics	18	4677	March 28, 2024

SketchUp Diffusion: Share your Feedback

Related topics