"Can we implement specific furniture brands to showcase real products in our designs using AI?"
Yes, you absolutely can! 😁
Here’s how you can do it:
➡️ Base Image: You can start with a real photo or an AI-generated image, like this living room setup.
➡️ Furniture Selection: Choose specific furniture references (just one single image is enough!).
➡️ Workflow Process: By masking the area where the furniture should go, the AI workflow restores the product based on its reference image and no extra prompting needed.
The result?
✅ 100% identical to the original product.
✅ Huge time-saver.
✅ Maximum flexibility for designers.
Remove - Replace - Iterate - Change - Add on a Still Image Using AI—Yes, It’s Doable and FREE! 😁
In my previous post, I explored an entire AI-powered post-production workflow for an exterior shot.
Now, let’s talk about interior images!
I took an old client render I made over 6 year ago and tested how much control AI can give us over transforming an image.
The results? Absolutely insane! 🤯
With just a few hours and one AI tool, I achieved a fully modified and refined version—without starting from scratch!
🔹 What I did:
✅ Removed elements
✅ Replaced furniture & decor
✅ Iterated different designs
✅ Changed colors & materials
✅ Added new details
🔹 How?
I used custom workflows inside ComfyUI—an open-source AI tool—and then combined all outputs seamlessly.
💡 The takeaway?
AI now offers remarkable control over post-production in visualization, and this is just the beginning! 🚀
Back in 2016, we took on an exciting challenge ... an international competition in Aarhus, Denmark.
It was the first phase of a School of Architecture design competition, where three winning proposals would later compete against Kazuyo Sejima + Ryue Nishizawa / SANAA, Lacaton & Vassal, and BIG - Bjarke Ingels Group.
🔹 The challenge? Present a strong conceptual idea—no plans, no technical details, just a clear vision.
Back then, I remember spending a couple of hours creating a Photoshop collage from a clay render of a mass model to better express the idea.
We didn't have enough time or resources to produce a high-end render.
Despite the constraints, I was amazed by the final result.
Today, I revisited this image and, with some AI enhancements, achieved this result in just a few minutes.
This reinforces my belief: AI is a powerful creative tool ... not a replacement, but an enhancement that frees up time for what truly matters: Creativity.
What do you think? Could AI change the way we approach early-stage architectural competitions?
Done Locally with ComfyUI
PS: And for those wondering ... no, sadly, we didn’t win the competition. 😅 But the journey was an incredible learning experience!
In this case, I took a render I made 8 years ago—and of course, I felt it could be enhanced.
Here’s how I did it:
🔹 Step 1: Adjust Framing & Composition
I extended the image using outpainting, allowing AI to perfectly fill in the extra space for a better composition.
🔹 Step 2: Iterations
I refined elements in the image to make them more cohesive. The key here? The "Denoising Value"!
1.0 → The model follows the prompt entirely.
0.0 → The model strictly follows the original image.
I typically adjust between 0.75 and 0.40, depending on the goal.
🔹 Step 3: Adding New Elements
I used inpainting to seamlessly integrate birds, a swimming pool, and people into the scene.
🔹 Step 4: Final Enhancements
To finish, I used an upscaling workflow to enhance details, improve resolution, and bring the image to life.
➡️ Base Image: AI-generated locally with ComfyUI — a living room setup.
➡️ Furniture Selection: I picked specific furniture references to implement.
➡️ Workflow Process: By masking each area and prompting “modern sofa”, “rug”, “armchair”, or “TV”, the AI model restored the furniture based on its reference image.
In the world of design, the “unfilled” isn’t empty; it’s an invitation
I’ve been working for a while to achieve this result, and finally, here it is
— thanks to the help of AI tools.I believe this approach could be incredibly useful in various fields:-- Design and architecture-- Interior design-- Marketing-- Real estate
In this case, I experimented with removing consistent elements from a random exterior image ... and the results are insane!The model perfectly reconstructs the hidden parts, even for reflections, based on the existing information in the image. It’s amazing to see this level of capability.
Imagine changing the light in a picture with a magic brush!
Just like telling a story in different ways can change how it feels, using AI lets us "re-light" an image to completely change its mood. Picture this: you start with a bright sunny morning scene, and with a few adjustments, you turn it into a cozy, late evening, or a misty foggy morning with soft, diffused light.This "magic" is the power of AI in architectural visualization.By using AI to adjust lighting, shadows, and even seasons, we can show a space’s potential across different moods and moments.