Nova3D, a system that generates 3D assets as executable Blender source code, produces a valid artifact for all 54 items in its Nova3D-Bench benchmark, with every asset exposing named parts in a parent…
Phi, a browser-native and desktop game engine with a Blender-style editor, Python scripting, and built-in Claude AI, has been released as a single opaque engine.wasm or native executable. The engine i…
Updream's Previs stage functions as a Blender for AI video creators, allowing users to build low-fidelity 3D scenes and set camera paths to guide AI generation, reducing failed shots and saving comput…
A developer rebuilt PolyForge, a standalone Python CAD tool, from a ChatGPT skill into an offline package that renders parametric part templates to OpenSCAD, FreeCAD, or Blender without requiring an L…
Tencent's Hunyuan3D team published WorldClaw, a system that turns text prompts into editable 3D worlds, but its core orchestration relies on Anthropic's Claude Opus 4.8 and OpenAI's GPT-Image-2, with …
StorageReview's lab-tested leaderboard of 2026 mobile workstations ranks the Dell Pro Max 16 Plus as Best Overall, featuring a 175W RTX PRO 5000 that delivered 3,875 Blender samples per minute and a S…
Jason Zhao launched Space on August 10th, a cloud filesystem for macOS that streams file data on demand into applications like Adobe Premiere and Photoshop, positioning it as 'what Dropbox was suppose…
Researchers introduced VideoCoCo, an agentic dual-engine framework that uses executable Blender code as a chain of thought to generate physically consistent videos. The system improved the OmniWeaving…
AI art tools like LLM agents and diffusion models should be used as collaborators, not replacements, to preserve human creativity, according to a practical workflow guide. The author argues that true …
Meshy AI's Image-to-3D feature lets users upload a product photo or sketch and receive a textured 3D mesh in minutes, replacing hours of marketplace searching. The workflow involves uploading a high-r…
NVIDIA has introduced Omniverse libraries, a set of software components that bring physical AI capabilities into existing 3D applications and prepare content for simulation, targeting developers and e…
NVIDIA announced that its Agent Toolkit now includes NVIDIA Omniverse libraries, giving AI agents tools to help developers integrate physical AI capabilities into applications and prepare 3D content f…
NVIDIA has released ovrtx, an RTX sensor simulation library now available as prerelease software on GitHub, enabling developers to generate camera, lidar, radar, and related sensor outputs from OpenUS…
NVIDIA announced at SIGGRAPH 2026 that six creative tools — Adobe, Affinity by Canva, Blender, Boris FX, Foundry, SideFX and Epic's Unreal Engine — have adopted the Model Context Protocol (MCP), enabl…
A developer released BlenderPulse, a free Windows overlay that automatically shows render progress, estimated finish time, and stall warnings for Blender 4.2+, disappearing when the job ends. The tool…
Researchers from an unnamed institution have developed ProcessSynthesizer, a method that uses large language models to generate procedural materials by reasoning over expert demonstration traces, outp…
ComfyUI is a node-based visual programming interface for AI image generation that lets users build custom pipelines by connecting processing nodes instead of writing code, supporting models including …
AI coding tools are flooding open-source projects with low-quality pull requests, overwhelming volunteer maintainers and driving some to quit. GitHub is exploring AI-based filtering to help maintainer…
A developer's field guide distinguishes between programmatic image generation via code and diffusion models. The guide advises using code for structured visuals like diagrams and charts, which are che…
A user demo on X shows OpenAI's GPT-5.6 Sol running Blender at 750 tokens per second, highlighting the model's low-latency performance in a live tool loop. OpenAI released GPT-5.6 Sol on July 9 across…