XOutlier
Download .zipAdd to Chrome

Bilawal Sidhu

@bilawalsidhu120k followers

decompiling reality; reconstructing real world events from public data. experimenting with vfx, sensing & robotics.

Open on X
Top outlier
298×
Best organic post
Peak views
13.2M
Single post
Bookmarks
153k
Across 99 organic posts
Last scan
Oct 17
Community cache
Posts 99 posts
#DatePost↓ OutlierViewsLikesRepostsBookmarks
1Mar 1, '23Before/after of Corridor's latest AI video is wild. They shot video on greenscreen, made virtual sets in Unreal, then reskinned it to anime by finetuning Stable Diffusion. Net resu298×13.2M15k2.8k3.2k
2Mar 25, '23Midjourney v5 has pushed into photorealism, a goal which has eluded the computer graphics industry for decades (!) 🤯 Insane progression, and all that by 11 people with a shared dr116×5.1M12k1.6k5k
3Jul 12, '24It’s wild that Aaron Swartz was aggressively prosecuted for scraping JSTOR articles. Meanwhile huge companies routinely scrape the public internet and sell it for $20/month and all69.7×3.1M56k9.5k5.2k
4Sep 17, '24Okay it happened! Snapchat Spectacles AR glasses. Fully standalone. 46 degree field of view. 37 pixels per degree. That’s roughly like a 100” TV screen! 2x snapdragon chips. 45 min60.3×2.7M2.8k3091.1k
5Aug 25, '23why is this so accurate 💀😭 #ai #chatgpt60×2.7M15k941782
6Sep 12, '25So India has this app called blinkit where you can get literally anything delivered in 10 mins. My mind is blown.56.2×2.5M23k7831.7k
7Dec 17, '24Everything here is 100% generated w/ Google Veo 2. I've got early access, and the visual fidelity and prompt adherence is genuinely nuts. Let's test it together and have some fun. 50.7×2.2M6.5k6332.9k
8Apr 25, '24Remember that 'air head' video made with Sora? Turns out it used a ton of rotoscoping and manual VFX. A 'head' would pop back on, and the balloon colors would keep changing from ge45.2×2M5.1k5131.4k
9May 28, '24❗EXCLUSIVE: "We learned about ChatGPT on Twitter." What REALLY happened at OpenAI? Former board member Helen Toner breaks her silence with shocking new details about Sam Altman's f45×2M3.3k6771.9k
10Feb 16, '24OpenAI just dropped their Sora research paper. As expected, the video-to-video results are flipping spectacular 🪄 A few other gems:42.4×1.9M9.9k1.2k2k
11Jul 5, '24RIP truth - it's been nice knowing ya31.7×1.4M6.6k1.1k2.4k
12May 30, '24Generative AI is super cool… BUT I’m continually blown away with the work happening in ‘procedural’ 3D modelling. Especially given these plugins are for a free (!) 3D tool like Ble30.9×1.4M9.1k9214.8k
13Aug 27, '25Since nano banana has gemini's world knowledge, you can just upload screenshots of the real world and ask it to annotate stuff for you. "you are a location-based AR experience gene29.7×1.3M3.9k3512.4k
14Oct 1, '24Pika 1.5 is pretty wild. When I said generative AI would let us edit reality, this is not what I had in mind... lol28.6×1.3M6.9k5672.9k
15Jun 9, '23Q: "After doing AI for so long, what have you learned about humans?" Sam Altman: "I grew up implicitly thinking that intelligence was this, like really special human thing and kind26.8×1.2M2.2k418818
16Sep 10, '25Apple will make some gorgeous AR glasses — they literally squeezed a whole phone into a mf-ing camera bump.25.9×1.1M10k339852
17Feb 21, '25The internet going wild with the microwave AI filter -- prolly because it's pure nightmare fuel 😭23.2×1M23k1.4k5.8k
18Jun 11, '24Ok I take it back. Apple’s ‘Private Cloud Computing’ actually takes ‘Confidential Computing’ to the next level. It’s SO secure that they can’t even comply with law enforcement requ22.9×1M4.6k6122.1k
19Nov 6, '25Google is now using Gemini to cross-reference ~250M places with Street View imagery to identify visible landmarks for turn-by-turn nav. Think iconic buildings, gas stations and res21.8×963k7.4k328881
20Mar 19, '233D capture is moving so fast - I scanned & animated this completely on an iPhone. Last summer you'd need to wrangle COLMAP, Instant NGP, and FFmpeg to make NeRFs. Now you can d20.8×920k3.3k3502k
21Jun 17, '25Veo 3 has digested the mother lode of ASMR content on YouTube making it an AI ASMR machine. This one got 3.1M likes and 12k comments in 3 days. Every popular YouTube format is abou19.3×854k3.1k2242k
22Jun 21, '25Adobe has quietly rolled out an AI camera app for iOS. Built by legends Marc Levoy (computational photography OG) and Florian Kainz (multi-academy award winner and creator of night17.7×784k4.6k2653k
23Feb 21, '25"When you ask your stoned roommates to put away the groceries" 😭17.4×770k10k576975
24Apr 12, '24AI has changed the meme game forever17.3×764k3.4k227532
25Mar 13, '25Blender MCP is here, allowing Claude to talk directly to Blender. For example, provide a 2D reference image and ask Claude to create it in 3D for you.17.2×761k7.1k7246.4k
26May 24, '243D capture is dope for media & entertainment, but the utilitarian applications might be even more impactful - literally x-ray vision making the unseen seen. With tools like Pix4D +16.6×735k4.1k5831.8k
27Jun 1, '23AI just took 3D modeling to a whole new level 🤯 Introducing Neuralangelo, a new AI model by NVIDIA that reconstructs mind-blowingly detailed 3D surfaces directly from 2D videos — 16.3×721k2.2k4351.1k
28Sep 23, '24This guy literally turned blender into a real-time 3d engine with multiplayer support When I say the merger of offline and real-time rendering is inevitable — this is not what I ex16.2×716k7k5632.2k
29Apr 27, '23🔥 Unreal Engine 5 is wild. Such a powerful tool for cinematic storytelling! 😻 📺 Made this short video entirely entirely in-engine with marketplace 3D assets, and a sprinkle of G16.1×714k1.5k197413
30Feb 27, '25Wow. Recreating the Shawshank Redemption prison in 3D from a single video, in real time (!) Just read the MASt3R-SLAM paper and it's pretty neat. These folks basically built a real15.9×704k7k8063.9k
31Mar 4, '23🧠 AI experiment comparing #ControlNet and #Gen1. Video goes in ➡ Minecraft comes out. Results are wild, and it's only a matter of time till this tech runs at 60fps. Then it'll tra15.4×679k2.4k432555
32Nov 9, '25Omg, AI videos on Douyin are a different breed. Chinese mom absolutely goes to town on a xenomorph 💀 And just when you think it’s over, it keeps escalating further:15.2×671k5.6k6892.1k
33Jun 4, '24When Apple said they were rolling out 'spatial media' this is what I actually expected - 3D video with six-degrees of freedom. Instead Vision Pro users got old wine (VR180 video) i15.1×666k1.8k2711.4k
34Aug 9, '25Damn it worked! Genie 3 world --> inpaint UI --> 4x topaz AI upscale --> train 3d gaussian splat You can step inside a painting of Socrates from 1787. Better than any imag14.9×659k7.8k7754.4k
35Apr 1, '23What a week for AI! Not yet scary, but a feeling is in the air. Things are heating up and people are conflicted. Why are the brightest minds in AI asking for a 6 month pause, while14.4×639k1.4k262912
36May 14, '24Sir Demis Hassabis just showed a super low latency demo of Google’s multimodal AI assistant on your phone AND augmented reality glasses. Clearly they’ve been cooking this for a whi13.3×589k1.5k226518
37Aug 29, '23Generative AI is cool and all, but I continue to be blown away by the strides in real-time visual effects. Case in point — ripping through immaculate fluid simulations on an RTX 4012.5×553k4.8k559721
38May 10, '23🚀 Big news today with Google + Adobe joining forces! We're talking about 3D content anchored to the real world at insane scale🌐 And of course, AI had a role to play. I've got ear12.4×548k2.3k629749
39Sep 25, '25Generative ai is cool but procedural 3d generation just hits different. iCity basically feels like sim city for adults who know blender.12.1×534k8k5224.4k
40Nov 11, '24Generative AI is cool and all, but procedural 3D modeling just hits different. Check out this Houdini setup by Pepe Buendia. Why this is cool: Instead of manually placing every bui11.9×528k8.1k7943.9k
42Jan 4, '25We’re basically building the matrix inside the matrix, aren’t we?11.4×506k3.4k269900
43Nov 10, '24Generative AI is cool and all, but procedural 3D modelling continues to hit the spot11.3×501k6.2k2901.5k
45Mar 3, '25The lines between code & content are blurring. I made this 3d city block animation in claude 3.7. Then I used runway gen-3's video-to-video to style it like a lego city at nigh11×488k4.9k4053.4k
46Jun 14, '24We finally know what happened at OpenAI last year11×487k4.2k348536
47May 8, '25Introducing VibeCon — the world’s largest vibe coding conference. Make sure you register today: http://127.0.0.1:8080/register11×485k13k928570
48Feb 21, '23I spent the weekend hacking an AI room makeover using ControlNet & Stable Diffusion, restyling my parent's "drawing room." How soon until this workflow is standard for home déc10.7×474k1.6k223649
49Mar 8, '25web graphics are cool and all but imagine vibe coding in blender 😍10.3×456k3.9k1731.3k
50Jun 4, '25Lmao. What niche even is this — grassroots dirt track racing meets google maps nerds? Veo 3 videos are seriously ridiculous and fun. Turn audio on for max enjoyment.10.2×452k5.2k3161.2k
51Feb 11, '25Typical Cursor user: “No, I said add it to the existing drop down menu, not a new one”10×442k6.9k304641
52Feb 20, '23ControlNet experiment where I'm toggling through different styles of contemporary Indian décor, while keeping a consistent scene layout. Loving how ControlNet is putting the artist9.8×434k1.9k260601
53May 31, '24The future of Street View looks like this 😍 Basically City-scale 3D Gaussian Splatting. Thanks to a hierarchical level of detail (LOD) approach, you get real-time rendering of mas9.7×430k1.7k194858
54Oct 8, '24The production value of these weather broadcasts is really next level — using unreal engine and in-camera VFX to put extreme weather events like Milton into perspective way better 9.3×412k3.5k325723
55Nov 14, '23Ask and you shall receive. Playing guitar in mixed reality. 🎸 So much potential to augment real world instruments. Why should pianos have all the fun? 😁 Awesome work by @sergeygl9.3×412k1.6k235416
56Jan 31, '24AR multiplayer FPS in China Who else loved paintball and airsoft as a kid? This would be so hype with none of the mess. Perfect for an urban community. And the P90s make it extra c8.7×385k1.7k236762
57Aug 5, '25Genie 2 vs Genie 3. Just 7 months between them. The bitter lesson continues to be bitter.8.6×381k3.8k3051.2k
58Apr 25, '23Wow! This looks SO much better than Roto Brush in After Effects, it's not even funny. Track-Anything is a video object tracking & segmentation tool based on Meta's Segment Anything8.5×377k1.9k313935
59Nov 13, '24I just love that this Matrix city project is a massive Houdini project masquerading as an Unreal project :-) Behold 100K+ simulated entities with an interconnected crowd & traffic 8.0×354k2.4k3021.3k
60Sep 6, '25Ngl this take aged like milk7.8×344k1.9k42198
61Dec 26, '23I'm still convinced the killer use case for 3d reconstruction tech is memory capture. No surprise Apple is headed in this direction. Here's a massive scan of the backyard + rooftop7.8×344k1.5k166669
62Jun 12, '25Woah. First person camera view being warped to a third person camera view using a unified flow and matching model.7.7×340k4k2711.5k
63Jul 29, '24LiDAR SLAM is so flipping cool Two different 3D maps captured by robots with an Ouster LiDAR puck + IMU + wheel encoders being merged together into one7.7×339k1.6k205685
64Sep 19, '233D scanning and rendering is moving so fast - got my splats up and running and I'm mind blown getting ~100fps for this complex 3D scene ⬇️ 🤯 1. WAY faster than NeRF: For compariso7.6×337k2k3051k
65Jun 13, '25AI stitching together multiple video feeds into one omniscient traffic god. This is what happens when cameras start talking to each other -- mapping the trajectory of every vehicle7.4×329k3.4k3461.5k
66Aug 5, '25Genie-3 just achieved what AAA game engines do - but WITHOUT any 3D models. Interactive REAL-TIME video generation @ 24 fps Wild how this model figured out complex effects like exp7.4×325k1.6k174907
67Feb 8, '233D, AI, NeRFs and oh my! Immersive view is now rolling out to 5 cities, with 5 more to follow. Experience the best of all views, with helpful info layered on top, so you can decide7.2×318k1.9k267345
68Mar 15, '25Andrej Karpathy: "Tesla actually does use a lot of expensive sensors, just at training time." Tesla amortizes the cost of LiDAR and other expensive techniques for offline mapping a7.0×310k1.7k115884
69Dec 26, '24X is erupting into a race war. Meanwhile, China just dropped an open-source AI model that absolutely MOGS, using a FRACTION of the compute US labs burn through. - US: "Restricting 6.9×306k2k240545
70Sep 22, '25Multi-camera shot generation will be a button in every video editor6.9×305k1.8k101904
71Oct 21, '24Prepping for a 25-minute keynote: I exported a PDF of my slides to Gemini 1.5 Pro and dropped in an audio recording of my dry run. Gemini gave me precise feedback down to the slide6.8×302k2k1562.7k
72Oct 17, '24Heads up! Mosaic dropped a pretty wild dataset of 1.26 million 360° images of Prague 🤯 If you're a researcher, creator or developer into 3D/AI/Geo, I think you're gonna wanna play6.7×296k2.4k2811.8k
73Apr 5, '23🤯 Wondering why creators like @SirWrender are losing their minds over @WonderDynamics? Short answer: it’s a middle ground between 3D, VFX and editorial tools ⚔️ So what took 3 day6.3×280k1.5k255733
74Jun 27, '25Nano is a depth-aware atmospheric haze plugin that uses ML depth estimation to add physically accurate fog and light scattering to your footage. Works *best* on log footage with vi6.2×276k4.3k3122.6k
75Nov 16, '24Finally a grounded take on AI & filmmaking from a Hollywood A-lister. I agree with everything Ben Affleck said: 1. Yes, AI will shatter barriers to entry. Budgets will drop, the nu6.0×267k1.8k4121.3k
76Nov 5, '24I can no longer walk around a city without seeing a machine-readable 3D model in my head. This is a geometric and semantic 3D model of San Francisco. These maps connect the world o5.9×260k2.6k1851.1k
77Nov 3, '23i'm convinced the killer use case for 3d reconstruction tech is memory capture my parents retired earlier this year and i have immortalized their home forever more photo scanning i5.7×250k1.8k199572
78Oct 22, '25So these researchers figured out you can basically hallucinate 3D cities into existence using just satellite photos & a diffusion model. The problem's pretty straightforward: satel5.5×242k2.7k2271.4k
79Feb 18, '25Bro is driving around a 3D Gaussian Splat of a city5.5×241k2.8k206863
80Mar 16, '25This is wild. Google's new Gemini model turns complex effects authoring into simple text prompts. Technical barriers gone - just describe what you want. Entire ComfyUI workflows no5.4×238k1.6k1161.5k
81Oct 24, '25Full circle moment. Six years of work on 3D maps and VR media -- seeds planted years ago turn into this. The Google team is absolutely crushing it.5.4×237k1.5k72524
82Feb 5, '25This is better than any Apple Vision Pro commercial5.0×220k1.8k90448
83May 20, '25Google Flow is the closest thing I've seen to a multimodal AI studio for creatives. And it’s available today. It feels like a generative camera and soundstage, where you can “captu5.0×219k2.4k2682k
84Nov 7, '25I genuinely think we’re on the cusp of a new type of creation engine. Feels less like prompting and more like puppeteering reality itself. MotionStream is a taste of what’s to come5.0×219k2.4k2351.2k
85Jul 13, '25We can just generate cities using open source 3d software and cheap plugins4.9×216k3.7k3292.2k
86Sep 27, '25Houdini is the OG of procedural 3D generation. The same tools Hollywood uses to build massive simulated worlds are equally useful as training grounds for robotics - reproducible ph4.8×214k2.7k2371.4k
87Jul 2, '25Walking around a big ass 3d gaussian splat of a hot spring in japan4.8×211k2.3k117721
88Jul 25, '25Google just discovered a powerful emergent capability in Veo 3 - visually annotate your instructions on the start frame, and Veo just does it for you! Instead of iterating endlessl4.1×181k2.1k1951.3k
89Dec 19, '2420+ labs just worked together to open source Genesis - a physics engine with a VLM agent that turns text prompts into interactive 4D worlds Think instant physics-accurate environme4.0×177k1.5k2021.1k
90Dec 23, '24Honestly, is there something you *can’t* do in Blender, because homie built a flight simulator in it 😭3.9×173k2k91450
91Apr 25, '25State of AI rn: - Google: Gemini 2.5 Ultra Pro Max Experimental is a total game changer, but you still have to name your google docs manually. - Microsoft: How many copilots can I 3.8×166k1.7k101316
92Jul 30, '25Google just took a big step towards building ChatGPT for Earth. AlphaEarth Foundations does something clever -- instead of drowning in petabytes of Earth observation data, it creat3.8×166k1.6k186959
93Jun 7, '25Exceedingly crispy multi-view 3D captures reconstructed beautifully (try it in browser below). Instead of the usual "deform one master model over time" approach (which breaks w/ fa3.6×159k2k2011.3k
94Aug 9, '25Genie 3 can basically do one-shot / single-image 3D reconstruction. Turns a 2D painting into an explorable 3D world, and holy crap the fidelity is nuts. No NeRF, no 3D mesh and blo3.1×138k1.5k118598
95Jan 3, '25Generative AI is cool and all, but procedural 3D modeling continues to hit the spot. Here’s the new ICity beta, which helps you harness the power of geometry nodes in Blender:2.9×127k1.8k122873
96Feb 17, '25"high-taste testers" feeling the agi2.9×126k1.6k45106
97Nov 12, '24Procedural 3D modeling is super cool, but you don't need to be a Houdini expert to take advantage of it. Here's a stellar Blender plugin called The City Generator by Andreas Dürr t2.8×126k2.5k2891.6k
98Aug 25, '25Using 3d gaussian splats to stabilize shaky handheld footage -- giving you the ultimate hyper lapse. New ai research (LongSplat)2.8×123k2.3k133872
99Mar 24, '25Vibe creating a 3D scene in Blender got even easier. Just provide a 2D reference image — LLM deconstructs the scene, figures out what 3D assets are needed, generates them using Tri2.6×113k1.8k2022k
100Mar 27, '25Who else is enjoying surfing the internet today? We should do this more often.2.3×102k3.1k172350
101Oct 16all I can think about after seeing the tesla roadster demo0.2×8.8k2391524

Scan another creator

@
@karpathy@levelsio@paulg@naval@marclou@illyism

Run this on any account.

XOutlier builds this table for every public profile you open on x.com, with live data and every post, not just the top 50.

Add to Chrome Download .zip