Alex Gorin (@anklovee) profile picture

Digital artist. Proud member of CLAN. https://xitter.cf/t.co/dp9M5dqAcy https://xitter.cf/t.co/Lu0R3uJWtA

Joined July 2010
Photo by Alex Gorin (@anklovee)Photo by Alex Gorin (@anklovee)Photo by Alex Gorin (@anklovee)Photo by Alex Gorin (@anklovee)Photo by Alex Gorin (@anklovee)Photo by Alex Gorin (@anklovee)Photo by Alex Gorin (@anklovee)Photo by Alex Gorin (@anklovee)Photo by Alex Gorin (@anklovee)Photo by Alex Gorin (@anklovee)
"Neon Dreams" w @13baym
2
5
1
27
Alex Gorin retweeted
SPLAT HUMAN、新キャラ「久我」 実在しない人間をどこまでリアルに3D化できるかという取り組みです。ブラウザで動かせます。#3DGS splat-human.vk.land/
12
58
4
500
23,861
Alex Gorin retweeted
No video models were used in the making of this scene. Here's how we're building realistic 3D scenes in Claude with Tesseract, thread below.
58
101
15
1,705
132,659
Alex Gorin retweeted
spatial outpainting
45
138
27
1,700
105,596
Alex Gorin retweeted
Amazon made 3D models of 7,953 real products it sells I packed all 165 GB into about 12 GB of GLB for three.js, WebGPU and web games, free on Hugging Face
43
180
21
2,289
125,964
Alex Gorin retweeted
試しにThin Film で 流体をシミュレーションしてみた。薄い膜の放射照度は美しいよ Cinema4D カスタムの流体ツール Octane
4
17
1
282
9,269
Alex Gorin retweeted
Now you can build any scene in Blender from a single reference image. I’ve open-sourced my tool AnyScene: drop in one or more references (plus optional text) and an agent builds the whole set inside Blender. Production-ready assets in a production ready environment, placed, lit and color-graded, with every asset broken out as its own file. github.com/apekshik/anyscene
21
112
7
1,230
60,247
Alex Gorin retweeted
🚨 one of the sharpest image to 3D models just went open source hi3d.ai/hi3d-1-0-open-source Hi3D V1.0 , this is Sparc3D from last year scaled up , code + weights now on GitHub / HF and it’s completely free to download and use , honestly the most interesting open 3D drop i’ve seen in a while i threw 4 of my own images at it , goku / charizard / the new roadster / the pelican on a bike Try it free @Hi3D_AI
🤝 Paid partnership
30
68
2
813
44,530
Alex Gorin retweeted
I've been testing Fibo 2 Edit Turbo with my texture projection software, and so far it has the best inpainting of any open-weight AI model I've tried. In my tests, it performs better than Qwen 2.1 and FLUX 3 Klein.
20
29
1
383
15,370
Following three years of development, FluidNinja LIVE-2 released - free to download at the community server #FluidNinja #UE5 #realtimeVFX #VFX #gamedev
91
431
41
4,275
505,633
Claude Opus 5.5への指示でBlenderで雰囲気あるコインランドリーの3DCGを作成しました。 Blenderを手動で操作することなく、すべてプロンプトだけで構築してみました。 基本的な制作の流れはリプで⬇️
80
449
85
5,225
739,583
Alex Gorin retweeted
Forget lidar. One single camera. Runs in real time & is open source: A streaming 3D model that reconstructs scenes live, at ~20 FPS, over long sequences. End-to-end. Optimization tricks, cleanup steps? Nope. And it beats both streaming and even some offline methods. Perception is becoming software-first. Closer to machines that see and understand the world as it unfolds. Thanks for sharing, @YinghaoXu1 📍Models: huggingface.co/robbyant/ling… Project page: technology.robbyant.com/ling… Code: github.com/Robbyant/lingbot-… Paper: arxiv.org/abs/2604.14141 —— Weekly robotics and AI insights. Subscribe free: 22astronauts.com
56
208
16
2,182
115,186
Alex Gorin retweeted
DistScene- turns a single image into an editable 3D scene. Uses sparse voxels, sparse DiT flow-matching models + LoRA. Based on TRELLIS.2 object-centric refinement restores details coolbeam.github.io/DistScene…
13
125
4
1,121
48,513
Alex Gorin retweeted
HOY UNA INDUSTRIA ENTERA DEJÓ DE TENER SENTIDO alguien subió a GitHub un repo que coge cualquier foto y te devuelve un mundo 3d explorable: mallas con físicas, splat del fondo, audio ambiente. todo. entra una imagen. sale un mundo. cinco minutos. la gente que lleva diez años aprendiendo Blender se ha pasado el día mirando esto en silencio. se llama image-blaster. os dejo el repo abajo.
255
2,466
220
21,639
1,612,837
Alex Gorin retweeted
Upscaling Seedance 2.5 480p Draft footage to 4K has never looked this good. 👀 Testing the new Starlight Fast 3 and Starlight Precise 2.6 Boost — and the results are seriously impressive. Full video in the comments.
🤝 Paid partnership · 🤖 Made with AI
New from Topaz Labs—upscale video faster than ever. ⚡️⚡️⚡️ Three massive upgrades across major video models in Topaz for Web. Plus, SDR-to-HDR conversion in Adobe Premiere Panel, Topaz for Android debuts, and more. See thread for full release.
23
24
1
292
31,112
0% AI. 100% 3D. Render Breakdown.
1
3
61
NVIDIA Open-source a model that rebuilds broken, blurry 3D scans from angles you never captured. like the 3D “auto-fixer.” It uses video diffusion to generate the camera angles you never captured, then reconstructs the scene from the generated frames. - 70x faster, Finishes in 1 to 4 steps - Beats SOTA by 3dB - you can use just text prompts - huggingface.co/nvidia/ArtiFi…
2
41
2
299
13,714
Alex Gorin retweeted
this AI upscaler on comfyui is absolutely crazy
125
353
13
4,199
294,887
Alex Gorin retweeted
ESTO NO DEBERÍA CORRER EN UN NAVEGADOR 121 millones de puntos. Un barrio entero de Praga reconstruido con Gaussian Splatting. Fotorealista. Caminable. Y está corriendo en el navegador… incluso en el móvil. PlayCanvas Engine (16.5k estrellas) + SuperSplat lo hacen posible. → Streamed SOG: carga progresiva, no tienes que descargar 1.3 GB de golpe → Renderer WebGPU que ordena y dibuja los Gaussians en la GPU → Colisiones reales (puedes caminar por el lugar) → Todo open source (MIT) Lo que hace 2 años solo se veía en engines nativos pesados… ahora se abre en una pestaña de Chrome. Este es el nivel real de 3D en la web en 2026. Repo del engine y codigo fuente ↓
9
49
5
360
21,735
What if every video you ever shot could turn into a permanent 3D hologram in the exact place it happened? I did it with photos first. Now I can do it with any video. Here’s a mama deer and her baby deer, filmed with my iphone a few days ago -- now floating as geo anchored holograms exactly where I captured them.
44
121
10
1,204
133,931