In this case ChatGPT has a big advantage in that the workflow is extremely simple, you throw everything together and tell it what to do. But the same problem, the original room changes in details and proportions. I would not say that for this task such changes are critical, for example, if we want at the initial stage of the project just to estimate how the interior will look like, ChatGPT gives an idea of it.

And yes, no model can handle some complex objects, the carpet is different here and there, but GPT is closer to the original. Also GPT better fits the lighting in the scene.

In #comfyui, the proportions of the interior and its original details are, of course, in place. But there is no speed advantage here, because you have to insert items one by one, not all at once as in ChatGPT, and wait for rendering each time. Besides, such workflow can be built only on Flux, and it is not fast by itself.

There are a lot of “Photoshop is dead” posts on the internet right now - you can edit images in LLM using just words. The story here is that even if the accuracy will be corrected in the future, the input of commands using text or voice is not suitable for any complex editing. Actually, people in the office do not communicate with each other in this way: to explain something properly you need sketches, masks, marks... in short, the functionality of Photoshop, otherwise no one will understand the task, neither a human nor AI (even if the AI will be smarter than a human, the problem here is not in intelligence, but in the fact that not everything can be formulated in words in a reasonable time). So AI model is not enough, you also need an interface with tools for graphical editing, that is AI inside the analogs of Photoshop, Revit, Rhino and everything else.

But, overall, sure cool, I still have some ideas on what can be done with these new ChatGPT functions

made a video about the current stage of 3D models generation with #comfyui

link to the custom nodes I used (there are also examples of workflow on the same github):
https://github.com/kijai/ComfyUI-Hunyuan3DWrapper

an overview of what you can do with #comfyui

How is the workflow of Rhino+Revit via Rhino.Inside organized?

In general, #revit uses standard families, both loadable and system, to represent geometry from #rhino, and they can be easily edited with the normal tools. In cases where standard families cannot be used (due to Revit limitations, as not every shape can be created in the family editor), the geometry is translated through DirectShape. DirectShape edit in Revit is no longer possible, but it is not a simple import, there are more possibilities: you can assign category, parameters, material from which you can then calculate volumes and areas.

On the example in the attached video DirectShape geometry used in a very minimal way. But this building is quite simple in shape, in other projects the situation may be different.

It is important that on any project, even a simple one, there are parts of the facade that cannot be done with standard Revit tools. And there are two ways out: to significantly simplify geometry or to keep details, but together with Rhino. Both options have the right to life depending on the project objectives and client requirements.

Project: Office building in Stuttgart, developed by Oliv and WENZEL + WENZEL
My part: developing facade geometry and BIM model for detail design phase