Jan Verwoerd
228 posts

Jan Verwoerd
@jan_bsc_
Founder of 360Fabriek VR/AR immersive studio. Specialised in the digitisation of objects and environments . 🤓👨🏻💻
Rotterdam, Nederland Katılım Ağustos 2015
1.2K Takip Edilen432 Takipçiler

I scanned a 13th-century fort with the #PortalCam
Here is what worked and what didn't
Let me start with some context on the scan. The overall process took 32 minutes. During the scan I tried to move closer to specific objects and features trying to capture more details and ended up walking 3 times on the battlements (not sure that was a good idea).
Initially, the RTX 3060 failed the reconstruction but after the upgrade to the #DellProMax T2 Tower equipped with an #NVIDIA RTX 6000 i got no issues (#DellTech for the win!).
👍 The final reconstruction ended up at 39,5M splats and the final .ply size was 2.6 Gb.
👍 Some of the features, like the gates, the well and benches, came up extremely well.
👍 The mesh generated by LCC studio was quite solid and allowed me to easily walk up the stairs and even jump on various areas of the fort.
❌ The scan was taken in October and the foliage made it very complicated to capture such a big area.
❌ Unfortunately, the HD features in LCC studio were not available yet so I couldn't test if the extra picture I took using a DSLR could complement the capture of the Portal Cam and increase the quality in specific regions.
❌ On one side of the battlements, the handrail came up kind of doubled. It seems as if the scanning that took place while walking on the top Vs the scanning on the ground level didn't align perfectly. If anybody has ideas on how to improve that, let me know.
My plan is not to clean it up and see if I can do some scenic relighting using @VolingaAI 🤔.
In case you have any other questions, let me know in the comments
English

For those in Europe, you will know how bad the technology media ecosystem is right now.
TechCrunch Europe gone.
The Next Web gone.
Financial Times not covering major funding rounds.
So we decided to rebuild it ourselves.
It's me and my buddy @lukeknight - we raised $150k.
And we're going to save European Technology Media.
etn.@etnshow
Allow us to re-introduce ourselves. Welcome to the European Technology Network.
English

Why digital nomads are rushing to Paraguay (and nobody's talking about it) 🇵🇾
While everyone's fighting for Portugal Golden Visas and Dubai residencies
Smart expats are quietly moving to Paraguay
The reason? Paraguay offers what most countries can't:
Residency in 60-90 days, with ZERO physical presence requirements after approval
But here's the part nobody tells you
You can maintain your Paraguay residency while living literally anywhere in the world
No mandatory stay. No annual visit requirements. Nothing
What you get:
✅ Temporary residency for 2 years + permanent after that
✅ Path to citizenship in 3 years
✅ 0% tax on foreign income (territorial taxation)
✅ Access to Mercosur (live/work in Argentina, Brazil, Uruguay)
✅ One of the cheapest residency processes in the world
No minimum income requirement, no local investment, nothing
Just show up and get your residency
The catch? You need to know the exact process... or you'll waste months dealing with bureaucracy
Want the complete Paraguay residency roadmap? DM me "PARAGUAY" 👇

English

I know a guy running AI street interviews as paid ads... 4.5x ROAS.
$0 spent on creators.
$0 spent on production.
Here's 11 AI video tactics brands are using to create viral ads for nearly $0:
1. AI street interviews (you can't tell they're fake)
2. Podcast-style clips that look 100% real
3. Viral food videos with zero kitchen
4. Anatomical video animations
5. Localization at scale — clone ads into any language instantly
6. Try-on videos without a single model
7. Shock hooks getting 47% higher completion rates
8. Product-style commercials
9. POV adventure content for travel brands
10. Real estate transformation videos
11. AI unboxing videos
Most marketers have no idea these exist yet.
I put together a free PDF with the exact prompts for all 11 along with the tool I'm using.
Comment "AI ADS" and I'll send you everything (must be following so I can dm you!).
English

@ai_uncovered I followed, shared and liked a while ago. You gonna share the templates with me?
English

🚨EXPOSED: 109s of Premium AI Agents.
If you missed it before, I'll give it again.
Worth $3K+ per build — now FREE for the first 2000.
Inside the file:
→ Booking & outreach automations
→ Scrapers, support agents & more
→ Cold email engines
→ Social listening dashboards
→ Lead gen bots
→ Content pipelines
→ Auto-scheduling assistants
→ AI copywriters
→ Form-to-CRM connectors
→ Data enrichment bots
→ Chatbot funnels
→ Review aggregators
→ Auto-reporting scripts
→ AI-powered survey analysers
Built-for-speed systems trusted by top agencies to land $7K+ clients.
Fill it up & GET:
- Comment "File"
- Like & Retweet
- Follow me @ai_uncovered to get DM Fast.
- No Comment = No DM, Move fast.
English
Jan Verwoerd retweetledi

i found a way to make AI videos that don't sound like AI...
example below....
sora 2, veo 3.1, kling 2.6 are decent but they all have that robotic AI accent that everyone can detect immediately
and when people try replacing the voices with elevenlabs, it always sounds way too professional
like it's recorded on a professional mic in a studio
but if i'm making a UGC video of someone in their room, i don't want studio quality
it should sound like it's actually in that room
the workflow i use completely removes that fake AI voice sound
why this matters:
when your AI voices sound too polished or robotic, people notice. their guard goes up. they disengage.
but when your voices sound like they're coming from a real person in a real room, that's when they work the best
i created a guide breaking down exactly how:
> to create voiceovers that sound completely real
> to replace fake-sounding voices in AI videos (not elevenlabs)
> to make voices sound like they're in the actual environment, not a studio
RT + reply "VOICE" and i'll send you the FULL guide (must follow so i can DM)
English

It’s still wip, but as promised here is the repo
A lot of experimentation is happening, I have 3 active versions:
1. Classic global radix sort
2. Local bitonic sort in threadgroup
3. Depth-first global radix sort
Everything stays on GPU 🍳
github.com/LuckyIYI/gsm-r…
English

@bilawalsidhu I might have a cool usecase already. Is it ready to spawn a scene based on the VPS? We already have the portalcam
English
Jan Verwoerd retweetledi

i’ve tested 99% of image gen approaches since I started making AI videos 6 months ago...
this is the BEST, repeateable workflow that works:
- curated shot references
- gemini 3.0
- midjourney
- freepik (nano banana pro)
it's honestly super simple but it's all you need to get the best possible image outputs imo
comment "IMAGE" + RT and i'll send you a my updated guide explaining the workflow (must be following)




English
Jan Verwoerd retweetledi

Nano Banana + N8N = AI Creatives Factory
This AI system creates scroll-stopping visuals at scale using Google's newest image model.
No designers. No agencies. No $50K creative budgets.
Just endless professional-grade ads that look like top brands made them.
Here's how it works:
→ Upload your product catalog to Airtable
→ N8N automation scrapes product details and images
→ Nano Banana creates multiple creative angles for each product
→ System generates different backgrounds, styles, and compositions automatically
→ All variations get organized in Airtable with performance tracking ready
Each visual pennies to generate.
You own 100% of the assets forever.
Runs 24/7 without touching it.
While competitors spend hours in Photoshop or pay agencies thousands per month, you'll be cranking out unlimited variations automatically.
Perfect brand consistency across every creative.
Built 100% in N8N.
Want the complete workflow?
Comment "NANO" + RT + Like
I'll DM you the entire N8N template + Airtable setup
(Must be following so I can DM)
Skip this and keep paying designers $200 per ad variation.


Marry Evan@marryevan999
We used to spend 15–20% extra every quarter on API issues — retries, timeouts, downtime. Then we made one change. API failures: 0. Here’s what we did 👇
English











