• zink released this 2026-11-12 11:44:54 +01:00 | 2 commits to main since this release

    Added

    • 3D models with fal.ai (generate_3d): from an image (a project file or one pasted into the
      chat, optional back/left/right views), from a text prompt, or from an image steered by a prompt
      (the image is refined with the prompt first – the 3D models take no text with an image).
      Styles textured, geometry (untextured, for 3D printing) and low-poly, optional PBR. Uses fal.ai's
      queue (takes minutes, with progress), saves a GLB plus a preview image, books the cost.
      Defaults: Hunyuan3D v3 image-to-3D / text-to-3D ([images] model_3d, model_3d_text); Tripo
      and Trellis endpoints work too.
    • The chat card offers "Open in the 3D view"; the media overview lists 3D models (also STL/3MF
      written by the agent) with their previews.

    Image: git.familie-zink.org/zink/codecraft:v202611-00024 (linux/amd64 linux/arm64).

    Downloads