So last WE, I went down into the Catacombs of Paris. If you're not familiar, it's an insane anthill-like network of 200 mi. of galleries and chambers, centuries-old, 60 ft beneath the surface. @NewYorker wrote about it in 2019: newyorker.com/news/dispatch/…. Here's a short story.
1/12
The goal was to 3D scan as many places as possible, using only the iPhone 12 Pro/LiDAR (and two powerful LED lights). And so we spent 12 hrs underground, walking (or crawling) more than 20 miles, and scanning 30 different places using @Scaniverse, @PolycamAI, and @Sitescape
2/12
All scans were uploaded to @Sketchfab and the whole series is available here: sketchfab.com/edemaistre/col…. Interestingly I was able to process all the scans immediately on the device, down below (without service). Cool way to demonstrate the power of LiDAR scanning w the iPhone
3/12
This provides an interesting 3D view of a hidden and secret part of Paris that very few people will ever visit. It's not quite legal and it can be pretty risky. This is the realm of the "cataphiles", experienced urban explorers cultivating a unique and secretive culture.
Entries into the catacombs are pretty rare, often locked, and always kept secret.
5/12
This is the "Fontaine des Chartreux", an underground fountain built 200 years ago under a former Carthusian monastery. @Scaniverse: skfb.ly/o66KN. Also scanned with @SiteScapeAI as a point cloud: skfb.ly/o66KP
6/12
Another nice place is the "Salle des Fêtes", also called "Salle du Cochon", a room where explorers gather to party or just take a rest. Captured with @Scaniverse: skfb.ly/o66GH. I met a famous TV journalist right there (won't say who :).
7/12
The catacombs are home to old shelters and bunkers that were used in former conflicts (especially by the German Luftwaffe and then by French Resistance). Here's an old nuclear fallout shelter ("Abri Falco"), that could host 100 ppl. W. @Scaniverse: skfb.ly/o66JZ
8/12
Catacombs were originally ancient underground quarries. After 1770, ossuaries were created to eliminate the city's overflowing cemeteries. 6 million people are buried there. This scan is the "Carrefour des Morts" (crossroad of death): skfb.ly/o66NL (w/ @PolycamAI)
9/12
"Cataphiles" like to create their own rooms. We stumbled upon this little room called "Our Lady of the Catacombs" with benches, an altar, and a wooden cross. Maybe some underground masses were celebrated here. With @Scaniverse, on @Sketchfab: skfb.ly/o66N8
10/12
Some places are REALLY tight. It's not for claustrophobic people. They are called "chatières" (only a cat - "chat" - can squeeze in). This one was 12m long and 50cm high. No turning back is possible. Scanning it with @Scaniverse was a challenge! skfb.ly/o66GV.
11/12
Check out other amazing 3D scans on the @Sketchfab collection (skfb.ly/o66XP). I've met a couple of other "scanners" that night. One wants to create a whole scan of the place. Another one is thinking about a VR game. Who knows what's next with this technology...
12/12
• • •
Missing some Tweet in this thread? You can try to
force a refresh
From multiple consistent objects within a single image to fully recreated 3D objects in Blender.
100% AI-generated.
Workflow detailed below 👇
Step 1/
Generate a grid of 6 consistent objects. For this, I used @Scenario_gg with the "Juicy Icons" model, which consistently creates cartoon-style, simplified 3D icons arranged in a grid.
Absolutely loving that this is happening during GDC week 😅. My schedule's packed with meetings & meetups, so not much time to vibe code, but I spun up a basic demo for a platformer jumping game, in minutes.
This was fully prompted via Claude 3.7 (on the left), zero manual tweaks. Link below 👇 and I'll keep sharing improvements and tips!
2025 is going to be a wild year for AI-powered game devs.
I used @JustinPBarnett's MCP on Github - check it out here
So far, it feels even easier than Blender, and I can’t wait to add more actions, assets, textures, and gameplay!github.com/justinpbarnett…
My main tip so far is that, just like with Blender MCP, you should proceed step by step >> one edit or element at a time.
Otherwise, Claude will go crazy and wil try doing everything at once (and fail).
Here are the key steps to creating stunning turnaround, using #Scenario ()
1/ Train or pick a character model (A).
2/ Optionaly>, pick a style model (B). Use it to create training images for (A), or you can merge both (A + B = C) for example.
3/ Utilize the custom model (A or C) to generate consistent characters. Then select a reference image to produce initial character turnarounds in your desired poses.
4/ Refine these initial outputs using Sketching and image2image.
5/ Select the best result and refine details in the Canvas for maximum consistency.
6/ Finally, upscale your final image (up to 8K resolution.)