Anthropic just rolled out creative connectors that hook Claude directly into heavyweight software like Blender, Autodesk Fusion, Adobe, and Ableton. Pros can now drive 3D modeling through natural-language prompts, search samples in Splice, and automate batch asset tasks inside Affinity. Why it matters: Anthropic is meeting creatives where they actually work, turning Claude into an integrated studio copilot rather than just a browser tab.
Researchers just introduced VIGA, a multimodal agent that turns 2D images into fully editable 3D scene programs inside Blender. By combining interleaved multimodal reasoning with graphics engine feedback, it can assemble scenes from basic geometric primitives or plug in existing 3D tools, beating standard baselines by over 124% on BlenderBench.
Nvidia just launched a workflow bridging Blender with the FLUX.1 image generator, allowing creators to guide AI images using 3D scenes. Instead of endlessly tweaking text prompts, you can place rough 3D models and set camera angles to lock down the layout. The catch is that it requires an RTX 4080 GPU or higher to run.
Researchers from ANU, Oxford, and BAAI just developed 3D-GPT, an AI system that translates text prompts into 3D environments. By deploying specialized agents to conceptualize scenes and write code directly for Blender, it automates procedural 3D modeling. It isn't photorealistic yet, but it signals a major shift toward text-driven asset creation.
