huggingface/meshgen

Use AI Agents directly in Blender.

What it solves

MeshGen allows users to control Blender using natural language, transforming complex 3D modeling tasks into simple text prompts. It positions AI as a tool to assist the artist rather than replace them.

How it works

It functions as a Blender addon that uses AI agents to translate text instructions into actions within the software. Users can choose between local inference (via llama.cpp or Ollama) or remote APIs (Hugging Face, Anthropic, or OpenAI). For advanced 3D capabilities, it offers optional integrations with LLaMA-Mesh for local mesh understanding and generation, and Hyper3D for high-fidelity 3D mesh creation.

Who it’s for

3D artists and Blender users who want to speed up their workflow by using AI to automate the creation and manipulation of 3D objects.

Highlights

  • Local and remote backend flexibility (Ollama, Hugging Face, OpenAI, Anthropic).
  • Integration with LLaMA-Mesh for local mesh understanding.
  • High-fidelity 3D generation via Hyper3D integration.
  • Direct installation as a Blender addon.

Related

  • Project
    sakalond/StableGen

    A Blender addon that integrates TRELLIS.2 and ComfyUI to generate 3D meshes from text or images and apply AI-powered textures to existing models.

  • Project
    nexu-io/codex-slides

    An open-source AI slide studio for Codex coding agents that transforms prompts, repos, or files into professional presentations through a steerable, live-editing workflow.

  • Project
    NVIDIA-NeMo/Megatron-Bridge

    NeMo Megatron Bridge is a PyTorch‑native library that connects Hugging Face model checkpoints with NVIDIA’s Megatron‑Core training engine. It offers bidirectional checkpoint conversion, verification, and high‑throughput training (tensor/pipeline parallelism, FP8/BF16/FP4). The repo ships ready‑made recipes for dozens of LLM, VLM, and diffusion models (e.g., Llama 3.2, Nemotron‑3 Ultra, K‑EXAONE‑2) and supports SFT/LoRA fine‑tuning. Install via the official NeMo Docker container or from source, and use the provided quick‑start scripts to convert, train, or export models.

  • Project
    tensorflow/java

    TensorFlow‑Java provides Maven‑publishable Java/JVM bindings for TensorFlow, including low‑level JNI wrappers (`tensorflow‑core`), a high‑level neural‑network API (`tensorflow‑framework`), and an independent ndarray library. It supports Linux (x86_64, arm64) and macOS (Apple Silicon) binaries, with optional GPU builds, and integrates with standard Java build tools.