ᴇᴅᴀɴ ᴋᴡᴀɴ

If you missed my Particle-Love at #3dfestweb, here is the live link: edankwan.com/experiments/pa… Motion Blur Everywhere!

New hire announcement [2/2]!! A big welcome to Yannic (@0beqz), who has joined Lusion as our Creative Developer! Yannic is a real time graphics developer at heart, with a passion for crafting beautifully realistic visuals on the web. He loves taking on complex technical challenges and turning them into immersive digital experiences. We are very excited to have you on the team, Yannic!

New hire announcement [1/2]!! We are delighted to welcome Pierre (@pierrenottin) to Lusion as our Creative Developer! Pierre loves working across 3D, design, and code. He is passionate about creating emotional and engaging experiences where the technology fades into the background, leaving space for design, motion, and interaction to shine. Great to have you with us, Pierre!

@N8Programs @threejs Is it a per-scene denoiser? I'm recently looking into small ML solutions for scene-specific rendering.

Excited to announce N8AO 2.0 for @threejs - the first major update to N8AO in years. This update adds a new neural denoiser for dramatically sharper, temporally-stable AO that greatly improves the definition of one's scene. Demo below:

AI money glitch: Selling tutorial courses on social media these days.

@mlperego @lusionltd @Faakinelle You will be missed 😢

A little announcement 📢 After more than 5 years at @lusionltd, I've decided to step into freelance life Huge thanks to everyone I've met along the way, especially @edankwan and @Faakinelle I could write a whole poem about how much these years at Lusion have meant to me, but honestly, the work we've put out during these years speaks louder than I ever could Let's see what happens now 🙃

Enjoying my last day of my 30-ish life. Goodbye youth.

@cortiz2894 Hmm.... igloo.inc by @abeto_co

Today I was working on some updates to my particle effect, adding physics Preview: hologram-particles.vercel.app Video Tutorial (Code in the description): youtu.be/iO-P2gEuOUc?si… Should I make a new video with this update in detail, or should we move on to a new project?

@daviddotli @krighxz @ugstuho Oh come on...

Paint with squishy sea creatures in Splash Canvas, a web toy I created for Google Arts & Culture. Play with it at goo.gle/splash-canvas Procedural audio by @krighxz, easel model by @ugstuho

Back when I was living in Hong Kong, the best way for me to get a good night's sleep was to turn on the AC to super cold and put on a thick blanket.

@designcoursecom @Samsyyyy @threejs So many "Claude did this" posts using ours and others work these days. All these social media platforms literally did nothing about it after reporting. Some even did meme coins with the work as well. What a time to be alive!

@Samsyyyy @threejs I'm going to make a youtube video about this.

Bro didn't just borrow inspiration, he took the whole lease 💀 Not the first time I was ripped, may not be the last 🫡 @threejs

@nicoptere Oh wait not commercial licensed.

@nicoptere I need this

now working in glorious WebGL! added the morph target and wasted a lot of time trying to *ahem* _improve_ the avatar generation ; I noticed the tooth & back were poorly reconstructed so I tried to synthesize and use multiple views & inject them at fitting time, not my finest idea

The Western models think that I am a creative technologist and the Chinese models thinking that I am a Hong Kong singer. Both kind of correct.

@RavenKwok First time bringing popcorn to see an art show. I need more drama.

🤨 x.com/i/status/19593…

@DavidSHolz Damn. People with good engineering skills and good designer eyes are rare. Really nice execution!!

we kept it a secret at leap motion that i filmed and edited all the videos myself - its been now ~10 years since i filmed and edited a video like this and i was honestly quite nervous that my skills weren't up to par for the task - but im very happy everyone seems to like it!

@tol__is @yugop Tha. One of the best shop in every old timer Flash folks' heart.

Can't believe @yugop, someone I've looked up to all along, liked this. 🙇‍♂️

@threejs I think creating something similar is doable, but the unique artistic choices made by the team vary depending on the project.

What if the AI is able to do this in 3 years?

@SebAaltonen @starmexxx But but but... what about "Le Chaton Fat" :D

@starmexxx And Fable 5 is on the doorstep. Which is a massive step above Opus 4.8. Yes, it's more expensive, but it's in a completely different league than local models fitting into 24GB consumer GPU. Even 512GB local models are way inferior, if you bought a $10k+ Mac Studio Ultra / similar

NVIDIA CEO JENSEN HUANG UNVEILED THE RTX 3090 AND THE USED VERSION ON EBAY NOW KILLS A $400/MONTH CLAUDE CODE AND OPENAI BILL the rtx 3090 has 24gb of vram, the same as a new rtx 4090 that costs $2,000. for local ai inference vram matters more than anything else and the 3090 sells for $650-800 used it runs qwen 3.6 27b comfortably, deepseek r1 14b at 60+ tokens per second and mistral 7b for fast automation. 16gb of qwen 3.6 fits with 8gb of headroom for long context alibaba's qwen 3.6 27b beats claude 4.5 opus on realworldqa vision 84.1 vs 77.0 and on ifbench instructions 76.5 vs 58.0. a free open weight model out-benchmarks anthropic's flagship a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and a used 3090 pays itself off in 3.5 months install ollama, pull qwen 3.6 27b, point claude code at localhost. same interface, nothing leaves the machine, nothing costs per request bookmark this and read the article below

Okay, someone applied to Lusion with a floppy disk + NFC chip. That's creative for sure.

@N8Programs For a 27b, isn't it even a 3090 works better?

Going to be playing around w/ Qwen3.6 27B running on one DGX Spark tonight. W/ MTP, it gets 800tok/sec+ prefill and ~25tok/sec decode. Very useful for some vibecoding.