IA Lab

AI experiments, AI+Art crossovers, and curated external articles about artificial intelligence and creative technology.

0 22 0 Comment on AniGen — The Tripo Team Just Solved AI 3D’s Dead-Statue Problem: One Photo In, a Fully Rigged Character Out

AniGen — The Tripo Team Just Solved AI 3D’s Dead-Statue Problem: One Photo In, a Fully Rigged Character Out

Every AI 3D generator on the planet hands you a beautiful, dead statue. Mesh? Gorgeous. Textures? 4K….

0 26 0 Comment on Aholo Viewer — Manycore Just Open-Sourced a Browser Renderer That Streams a Billion Splats, No Install

Aholo Viewer — Manycore Just Open-Sourced a Browser Renderer That Streams a Billion Splats, No Install

The Hook A billion Gaussian splats. Streaming. In a browser tab. On your phone. With no install,…

0 27 0 Comment on MoZoo — A Diffusion Model Just Did Fur and Muscle Sim From a Coarse Mesh, and It Works for Kibble

MoZoo — A Diffusion Model Just Did Fur and Muscle Sim From a Coarse Mesh, and It Works for Kibble

Animal fur and muscle have always been the wall every CG studio hits. A believable tiger means…

0 36 0 Comment on Rodin Gen-2.5 — The First 10-Million-Polygon AI 3D Model, and Its Best Trick Isn’t the Geometry

Rodin Gen-2.5 — The First 10-Million-Polygon AI 3D Model, and Its Best Trick Isn’t the Geometry

Rodin’s pitch in one image: production-ready 3D from a prompt or a photo. Source: Hyper3D Hook On…

0 27 0 Comment on Project Genie Just Grounded Its Dream Worlds in Real Streets — Pin a Place on the Map, Walk Into Your Own Version of It

Project Genie Just Grounded Its Dream Worlds in Real Streets — Pin a Place on the Map, Walk Into Your Own Version of It

Two months ago we wrote that Genie 3 had turned text into interactive 3D worlds. Google just…

0 26 0 Comment on HiDream-O1-Image — The 8B Open Model That Reasons Before It Draws (and Beats FLUX.2 at a Quarter the Size)

HiDream-O1-Image — The 8B Open Model That Reasons Before It Draws (and Beats FLUX.2 at a Quarter the Size)

Every few months an open model shows up and quietly embarrasses something four times its size. This…

0 25 0 Comment on Pixal3D — Tencent’s SIGGRAPH 2026 Model Stops Guessing and Nails Every Pixel to Your 3D Mesh

Pixal3D — Tencent’s SIGGRAPH 2026 Model Stops Guessing and Nails Every Pixel to Your 3D Mesh

Most image-to-3D models still treat your input photo as a suggestion. They squint at it, extract some…

0 33 0 Comment on Reallusion AI Studio — The Bet That 3D Artists Directing AI Will Beat Anyone Typing Prompts

Reallusion AI Studio — The Bet That 3D Artists Directing AI Will Beat Anyone Typing Prompts

For three years the AI video pitch has been the same: type a sentence, get a clip….

0 41 0 Comment on SAM 3D Animal — Meta’s Segment Anything Just Learned to Pull a Whole Herd Out of One Photo

SAM 3D Animal — Meta’s Segment Anything Just Learned to Pull a Whole Herd Out of One Photo

Reconstructing a single object from a photo is hard enough. Now imagine eight overlapping dogs in a…

0 35 0 Comment on VARCO 3D — The Studio Behind Lineage Just Shipped Text-to-Animated-3D in Your Browser, for 35 Cents an Asset

VARCO 3D — The Studio Behind Lineage Just Shipped Text-to-Animated-3D in Your Browser, for 35 Cents an Asset

Hook Most text-to-3D tools hand you a frozen mesh and wish you luck. VARCO 3D hands you…