localai-org/kimodo.cpp

Animate skeletons with natural language; NVIDIA's Kimodo ported to C++/GGML

What it solves

It provides a high-performance, C++ implementation of NVIDIA's Kimodo text-to-motion model, allowing users to generate human motion sequences from text prompts on local hardware without needing a heavy Python environment.

How it works

The project uses the GGML/C++ framework to run the Kimodo model. It can take either a UTF-8 text prompt or a precomputed LLM2Vec embedding as input. It then generates SMPL-X22 local rotations and root translations, which represent human movement. The system supports execution on both CPU and Vulkan-enabled GPUs to optimize performance and VRAM usage.

Who it’s for

Developers and researchers working with human motion synthesis, 3D animation, and embodied intelligence who need a lightweight, local inference engine for text-to-motion generation.

Highlights

  • Hardware Flexibility: Supports both CPU and Vulkan for acceleration.
  • C/C++ APIs: Provides a native API for integration into other software.
  • GGUF Support: Uses the GGUF format for efficient model loading and weight management.
  • Integrated Demo: Includes a local web-based demo for testing prompts and managing animation history.

Related

  • Project
    kigner/audio.cpp-webui

    A high-performance C++ audio inference framework based on ggml that enables fast, portable local execution of TTS, ASR, and voice cloning models across multiple hardware backends.

  • Project
    mudler/parakeet.cpp

    A C++17 inference port of NVIDIA's NeMo Parakeet speech-recognition models that provides fast, dependency-light ASR on CPU and GPU without requiring Python.

  • Project
    foldl/chatllm.cpp

    A C++ LLM inference engine based on ggml that enables memory-efficient local execution of multimodal models with RAG and quantization support.

  • Project
    nv-tlabs/kimodo

    A kinematic motion diffusion model that generates controllable 3D human and robot motions using text prompts and kinematic constraints.

  • Project
    ServeurpersoCom/acestep.cpp

    A local AI music generation server powered by GGML that turns text descriptions into stereo 48kHz audio using the ACE-Step 1.5 models.