Claude Fable 5.1 Builds a Browser 3D City as Code
PhiloLabs used Claude Fable 5.1 agent swarms to generate an explorable, MIT-licensed browser 3D city, Union Square SF, as Three.js code you can run and fork.
World Labs Atlas: One Omni Model for Video and 3D
World Labs launched Atlas, an omni model that natively handles text, image, video, and 3D in one system. It is in early access with select partners.
ComfyUI Adds Native Trellis.2 and Pixal3D 3D
ComfyUI now ships Trellis.2 and Pixal3D as native nodes, turning a single image into a high-fidelity 3D asset with full PBR textures and mesh cleanup, running locally at zero cost per asset.
How to Control Blender With an AI Agent via MCP
Hand your 3D scene to an AI agent and build by conversation. This tutorial connects Claude or Cursor to Blender with the open-source MCP server in about 15 minutes.
V2Fun: AI 3D Character Generator With Motion Capture
V2Fun turns text, images, and video into rigged, 8K-textured 3D characters with AI motion capture, launched July 15, 2026 on Product Hunt.
ComfyUI v0.28.0 Adds 3D and Splat Export
ComfyUI shipped version 0.28.0 on July 15, 2026 with native 3D and Gaussian splat export, new text nodes, SeedVR2 upscaling, and more open-model support.
Google Open-Sources Noto 3D Emoji as OBJ Files
For World Emoji Day, Google rebuilt all 3,977 Noto emoji as true 3D models and released them as raw .OBJ files anyone can open in Blender. Here is what shipped and how creators can use it.
Avatoon: 3D Avatar Lip-Sync in React Three Fiber
Avatoon is an open-source React Three Fiber component that drops a talking, lip-synced 3D avatar into any web or React Native app. Version 1.10.0 shipped July 15, 2026 under an MIT license.
Trellis2.c: Local Image-to-3D With No Python
trellis2.c runs Microsoft's TRELLIS.2 image-to-3D model natively on CUDA or Vulkan with no Python, chaining four models into a full local pipeline from photo to rigged 3D asset.
Drafted V2 Generates AI Home Plans in 2D and 3D
Drafted has released Drafted V2, a faster AI home-design tool that turns a list of rooms into complete 2D floor plans and interactive 3D models in seconds.
Text-to-CAD AI: Turn Prompts Into Printable Models
Yes, AI can turn a sentence into a real 3D model you can print, but only some tools give you a model you can also edit. The split that decides everything is parametric versus mesh.
How to Turn a Photo Into a 3D Splat for the Web
Turn a single photo into an interactive 3D Gaussian splat you can embed on a live web page, using free open-source tools: TripoSplat, ComfyUI, and SuperSplat.
Maket AI Floor Plan Upload Turns Images Into 3D
Maket's new Floor Plan Upload uses AI to turn existing PDF, JPG, or PNG floor plans into editable, dimension-accurate 3D layouts in minutes.
ComfyUI Gets Native 3D Gaussian Splats with TripoSplat
ComfyUI added native support for TripoSplat on June 1, 2026.
Reallusion AI Studio: 3D Control Layer for AI Video
Reallusion launched AI Studio on May 25, 2026, pairing iClone 3D animation tools with ByteDance Seedance video generation for 3D-controlled AI video.
Antigravity 2.0 Beats Codex on 3D CAD Benchmark
Google Antigravity 2.0, the agent-first desktop platform from I/O 2026, took the top score on a new OpenSCAD 3D CAD benchmark over Codex 5.5 and the rest of the field.
Pixal3D Open-Sources Pixel-Aligned Image-to-3D Model
Tencent ARC open-sourced Pixal3D, a SIGGRAPH 2026 image-to-3D model generating high-fidelity meshes from single images.
Odyssey Agora-1: 4-Player AI World Model You Can Play
Odyssey released Agora-1 on May 18, 2026, a multi-agent world model that lets up to four people share and interact inside the same AI-generated simulation in real time. Built on GoldenEye, it splits simulation from rendering using a DiT model.
Image-Blaster: One Image to 3D Worlds for Claude Code
Open-source Claude Code skill turns one image into a fully meshed 3D scene with separate object meshes, Gaussian splat background, and ambient plus physics audio in under five minutes.
Tripo 3.1 Lands in ComfyUI: PBR 3D Assets in 3 Workflows
Tripo 3.1 is now available in ComfyUI via Partner Nodes, adding high-density geometry and PBR-ready 3D to text-to-model, image-to-model, and multiview workflows.
Claude for 3D Artists: Blender, Fusion, SketchUp Workflow in 2026
The April 2026 Claude for Creative Work launch covered three 3D apps: Blender, Fusion, SketchUp. This is the working 3D artist's complete pipeline guide.
Alibaba Happy Oyster Lets You Walk Through AI-Generated 3D Worlds
Alibaba's Happy Oyster generates navigable 3D environments and interactive video from text prompts, letting creators walk through and direct AI-built worlds in real time.
Maxon Launches Cinema 4D for iPad Beta at NAB 2026
Maxon announced Cinema 4D for iPad at NAB Show 2026, opening beta registration for the first professional 3D application on iPadOS.
Maxon Releases Autograph for Free: Motion Graphics Tool for Individual Creators
Maxon releases Autograph 2026.0 free for individual artists on April 15, 2026. USD-based motion graphics and compositing, no subscription required.