topic Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback in Visualization

Native ArchiCAD AI Visualization Plugin - Seeking Feedback

mike_linespire — Sat, 24 Jan 2026 12:16:07 GMT

Hey everyone,

I've built an AI archviz addon for ArchiCAD that is using the latest Google models. As primarily a building designer, I wanted an addon that streamlined creating the image directly in ArchiCAD and placing it on the coversheet layout for our projects without needing to export/import.

I've played around with these AI models from the start and always been disappointed that whilst they were impressive, they weren't accurate enough to share with clients (missing windows, roofline changes, wrong materials). The latest models from Google are the first time I've felt they are producing client ready images (9 times out of 10!).

I'd love some feedback on the tool so I've setup a free trial that includes 5 image generations (reach out and I can top you up with a couple of extras if you need them). I'm going to get a macOS version going as soon as I can too.

There is a before/after slider on the website where you can see how accurate the AI model is at matching the geometry of the ArchiCAD model

Operating system used: Windows

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

Botonis — Sat, 24 Jan 2026 21:57:04 GMT

Always intersted. I really would love to give it a try!

Are you referring to Gemini?

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

mike_linespire — Sat, 24 Jan 2026 23:02:24 GMT

Hey Botonis,

Yep its using Gemini 3 Pro Image (nano banana pro) at the moment which I've been really impressed with. I've set up the plugin so I can always swap in whatever AI model is working best for archiviz at the time.

Let me know if you give it a go!

https://www.linespirereflect.com/

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

PB — Sun, 25 Jan 2026 08:54:34 GMT

Hi Mike,

Most promising. Please let us know when you have a Mac version to try out.

Some questions: (from an AI neophyte)

1) Can you "lock-in" the elements added by AI so that they are consistent through different views?

2) Can the process insert a design into an existing site? (from photos, aerial images, surveyors data, etc.?)

3) Could the process be adapted to upload a 3D model and generate views & video rather than working directly from a fixed 3D view?

4) your thoughts on pricing for those of us who may not need it on a regular basis?

Many thanks

P.S. How is copyright, privacy, and intellectual ownership handled? (from the Google side - your terms are clear on your site)

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

rkres — Sun, 25 Jan 2026 08:55:57 GMT

I'll also give it a shot, thank you for sharing your work.

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

rkres — Sun, 25 Jan 2026 10:56:07 GMT

I second the option to lock in elements, for more consistend shots.

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

mike_linespire — Sun, 25 Jan 2026 13:17:32 GMT

Hey PB,

These are great questions!

1) This is a tricky one and something I've had to battle with in my own projects. The AI can be very consistent if it recognises the Archicad element and its association in the prompt is strict. So for example if my Archicad model had a vertical weatherboard surface and my prompt said "James Hardie Axon 133mm in Dulux Vivid White", it should be able to keep that material consistent in 2 different images. Where you would definitely have problems is with elements added entirely by AI. For example if you were generating an image of a pool area from 2 different angles and prompted "add floating pool toy", you would likely end up with totally different pool toys in each image. If you need something to remain consistent across both images its best to add a 3D element to the model that the AI model can reference and then be specific about it in the prompt.

2) AI can definitely do this, Gemini 3 Pro Image can do this particularly well. It's not something you could do from my addon yet though because you'd need to be able to add reference images which isn't possible yet. Its a great idea for a future feature I can work on.

3) I'm not sure I understand exactly what you mean but a feature I'm looking into being able to work with archicad camera views instead of just capturing the 3d window. That way you could setup all of your camera views in advance and then process them together with the same prompt.

4) I'm definitely going to think more about pricing in the future. I think it would make sense to have a cheaper tier with less credits or a longer term tier for people that need it more infrequently.

Google's privacy policy is actually quite positive. They claim they will not use the data to train any AI/ML models or retain the data (subject to some specific terms) . I made sure it was clear on my website which API we're using because I think its really important that people know how their intellectual property is being processed. Here is a link directly to their privacy policy if you're interested: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/vertex-ai-zero-data-retention

Thanks again for the questions. The macOS version is top of my list and hopefully won't be too far away. I'll keep you posted

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

mike_linespire — Sun, 25 Jan 2026 13:23:09 GMT

Hey rkres,

I mentioned this above to PB but something you can try is adding a 3D element in the Archicad model of what you want to stay consistent and specifically mention it in your prompt for both images.

For example if your prompt includes a feature tree in the front yard, add a tree model where you want it to be and then in your prompt say something like "tree in front yard is a mature olive tree"

Consistency is definitely the hardest challenge with AI generations though. Let me know how you go!

Thanks

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

rkres — Sun, 25 Jan 2026 14:05:20 GMT

Thank you for the advice, that makes sense.

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

PB — Sun, 25 Jan 2026 14:22:51 GMT

you for your clarifications, Mike. I look forward to the Mac version.

On my third question, I'm trying to ascertain two things - if you can help:

a) Your example shows the landscaping (driveway, planting, etc.) into which your model is integrated. As & when the AI comes up with a good design proposal, ideally we could then instruct that the design elements visible - including the 100% AI items - are kept for following renders or iterations. So , for example, the driveway is an attractive design, hence we would like it to be exactly the same on the next render which is from the other corner of the house from which the drive is still visible.

b) By using a 3D model (native PLA, IFC, Datasmith, 3DS, etc.) is it currently possible for the AI to "adopt" the model and create its set of textures, setting, people, vegetation, etc. so that a consistent set of stills & video can be generated from it. I'm guessing not by your response, and from what I have seen on the internet, although I suspect we can't be too far away from that. My reasoning being that if the 3D model is treated by AI in the same way that an Enscape ot Twinmotion model is created, we then have consistency across renders & video. Perhaps this is something which would need to be developed by Chaos or Unreal to anchor the AI input to the 3D model?

Thanks again for sharing your work and I wish you every success.

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

PB — Sun, 25 Jan 2026 14:54:03 GMT

Now that my curiosity is piqued, I've had a look through the current Enscape & Twinmotion websites. They are both adopting AI within their products. Nothing to see yet for Twinmotion and the Enscape AI generated landscapes look too "Midjourney" for my taste...again, not sure how consistency works across different views/renders for the AI generated input.

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

mike_linespire — Mon, 26 Jan 2026 01:30:02 GMT

Hey PB,

I think D5 are probably doing the most interesting AI tools at the moment. Their latest release can generate 3D assets from reference photos: https://youtu.be/Z3c7lDY98oY?si=A13Hxxgx4nDD0iJO&t=112

I would LOVE to be able to do something like this with Archicad GDL objects and maybe it will be possible in the future.

I know what you mean about the "midjourney" look! Google really raised the bar with Gemini 3 Pro (particularly for archviz) but I'm sure the other models will catch up.

Thanks

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

PB — Mon, 26 Jan 2026 11:24:19 GMT

Thanks Mike.

Yes, D5 shows the way forward - sadly, Windows only…

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

Aaron Bourgoin — Mon, 26 Jan 2026 13:04:53 GMT

I recall when D5 launched, the developers explained that while they were interested in supporting the Mac platform they wouldn't until Apple. hardware was strong enough. I wonder what they think now.

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

mike_linespire — Sun, 22 Feb 2026 01:57:53 GMT

Hey Everyone,

Just an update to let you know the the macOS version is ready and up on the website (www.linespirereflect.com) if you'd like to give it a try. Took a fair bit longer than I thought to get a Apple Developer account so I could publish it. Also I've only been able to test this on a Intel-Macbook but it should be fine with the new Apple Silicone as well. Let me know if you have any issues.

In the mean-time I've also added a few new features to try:

-Before/After slider directly in the add-on so you can verify the accuracy of the produced image

-4k Upscale

-Updated the place on layout to work more intuitively

-Reference Image - you can upload a reference image that the AI model can use to copy lighting/materials/image style.

A couple of known issues:
-When using a reference image, the model can get confused and produce an amalgamation of your archicad view and the reference image rather than just copying the style/mood etc - Changing your archicad model to linework or whitemodel can help avoid this.

-When using the reference image, the final render will match the aspect ratio of the reference image instead of the archicad view. I'm working on a fix for this now.

A massive thank-you to everyone that has tried it out and provided feedback. My next goals are to add an editing workflow for making small changes to the images after they are produced and to overhaul the UI to be more intuitive.

If anyone has any other features that like to see, I'd love to hear about it.

All the best!

Michael

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

rkres — Sun, 22 Feb 2026 07:02:08 GMT

thats great, cant wait to try the new features out

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

PB — Mon, 23 Feb 2026 10:03:21 GMT

Many thanks for the heads-up: I'll give it a try this week...looking forward to seeing how it works...

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

marcoariveross — Mon, 23 Feb 2026 14:12:24 GMT

The creators of D5 were referring to the video card. They, like many others, take better advantage of ray tracing or patch tracing with NVIDIA's CUDA technology, and Apple doesn't use that technology (at least that's what I knew). AMD cards are cheaper and excellent graphics cards, but I think their technology still isn't quite up to par.

Re: Native ArchiCAD AI Visualization Plugin - Seeking Feedback

mike_linespire — Fri, 13 Nov 2026 00:56:18 GMT

[Moderator: The post contains advertisement for a commercial product.]

Hey everyone!

Another update on Linespire Reflect. Version 1.1 is out now, and it’s easily the biggest update since launch. A lot of this came directly from the discussion in this thread and emails from you guys, so thank you.

(new UI - includes render history and new tabs for setting up, editing and then animating)

Back in February I mentioned that a UI overhaul and an editing workflow were next on the list. Here is where things have landed, along with a few major additions to what the plugin can actually read from Archicad:

2D Views (Plans, Elevations & Sections): Reflect isn't limited to the 3D window anymore. You can now render floor plans, sections, elevations, and interior elevations directly. I’ve built in a few starting presets (like Brochure Plan, Site Plan, and Rendered Joinery Elevation), and you can tweak those or save your own.
Whole Layouts & Sheet Consistency: You can now capture an entire layout sheet, pick which drawings on the sheet you want to process, and render them all together in one pass. @PB and @rkres, this is a step toward the cross-view consistency you both asked about earlier - because the drawings are processed together, the AI keeps materials cohesive across the whole sheet. (Separate 3D camera views are still the tough nut to crack, though!). It can drop the results onto a new "Rendered" copy of your layout, or layer them cleanly over/under your existing linework.
Touch-Up Brush (Beta): You can now paint over a specific area, type what you want changed, and only regenerate that spot. Right now it’s best for small fixes—like scrubbing out a random object or removing stray text - plus the before/after slider now directly compares your edits.
Archicad 30 Support: Now running on AC 30 for both Windows and Mac (alongside 23–29 on Windows and 26–29 on Mac), plus a fix for an occasional crash on exit.

A couple of known issues to be upfront about:

The new Touch-Up brush still struggles with large, continuous surfaces, like trying to swap the material on a whole wall or a soffit. The edge blending isn't quite reliable enough for that yet, so a whole-image prompt edit still works better for big material swaps.
On very wide-angle views, the AI will still occasionally try to shift the camera framing - I've added a "Prioritise Camera Angle" that will mitigate this but gives the AI less freedom which can hurt the image quality.

Where my head is at for the next versions: A huge chunk of your feedback has been around editing the output once you have a render you mostly like, and that’s my main focus going forward. I’m currently testing more "Photoshop-style" selection and masking tools. The goal is to make it much easier to rein in AI hallucinations when it goes rogue on a detail, or to quickly update a specific part of a render after client feedback or a design change without having to re-roll the whole image.

I’ve put together a proper write-up with visual before/after examples here:https://www.linespirereflect.com/blog/linespire-reflect-1-1

(And if you just want to poke around without installing anything in Archicad, I also added a free sample project you can test directly in the browser: https://www.linespirereflect.com/dashboard/render).

As always, I'd love to hear what works and what breaks, especially on the new 2D plan and layout workflows! I've added a 👍👎 system directly into the addon so you can let me know what's working. It also gives the option to send your source image, prompt and output in an email to support@linespirereflect.com if you want some direct feedback from me.

For those of you testing AI in practice (whether in Reflect, or if you've been trying out Graphisoft's new built-in visualizer in v30 - I'm on a perpetual licence myself so I haven't been able to take it for a spin yet): what’s the #1 edit or fix you find yourself needing to make after showing a first pass to a client? Knowing where the biggest friction is will help me figure out which editing tools to prioritize first.

All the best,
Michael