skin-tokens.cpp

kimodo.cpp is a C++ and GGML implementation of NVIDIA's Kimodo text-to-motion model for local CPU or Vulkan inference. It accepts UTF-8 prompts or precomputed 4096-value F32 LLM2Vec embeddings and generates root translations plus local XYZW rotations for several control skeletons, including SMPL-X, SOMA, and Unitree G1 formats. The project includes GGUF model loading with validation, Safetensors conversion, DDIM sampling, conditioned multi-prompt transitions, C and C++ APIs, CPU/Vulkan parity tests, skeleton-only GLB export, and a local browser demo. Its native API returns the joints predicted by the selected model; features such as general constraint input, SOMA's 77-joint expansion, skinned-mesh GLB export, and quantized models are not implemented.

Kindergrimm is an open-source procedural drawing system and game project for hand-drawn doodle characters on cream paper. Each face is represented by a JSON recipe containing a seed, medium, color, and parts; the same recipe redraws the same character and can be saved, shared, or rebuilt at runtime. Drawing uses wobbling, dry-granulated ribbon strokes and techniques such as hatching, scribbling, stippling, graphite, wash, oil daubs, chalk, and marker, while separate medium data controls tone, skin, and edge treatment. Character parts are converted by a generic rig into bones and meshes, and the animation system supports boiling, blinking, gaze saccades, talking, swaying, and breathing. The repository includes a face editor, crowd viewer, item-review contact sheets, and three linked scenes or games: Kindergrimm, Marbles, and Orla. It is released into the public domain under the Unlicense.

Procedura is an open-source agentic 3D-modeling tool from SpatiaOS that converts text prompts into editable procedural assemblies rather than point clouds or triangle meshes. It generates OpenSCAD source with named parts and typed mates, plans and builds parts incrementally, and can use reference images and optional Blender render feedback during refinement. Optional passes assign per-part PBR materials and plan articulation, exporting motion to OpenUSD and URDF with Isaac-based validation. It runs locally as a Bun/TypeScript pipeline using a configurable OpenAI-compatible, Gemini, or local model endpoint; it does not provide hosted inference or API keys. The pipeline uses a Manifold-capable OpenSCAD build to compile the generated programs and Blender for renders, and includes a web Studio for composing runs and inspecting intermediate artifacts. The repository is MIT-licensed.

Gigatoken is an open-source tokenizer for language-model training data, implemented in Rust and distributed as a Python package. It tokenizes large text corpora at gigabytes per second, supports common tokenizer formats across x86 and ARM hardware, and provides compatibility modes for Hugging Face Tokenizers and Tiktoken. Its native API can read text files directly and encode them with parallel processing, while the compatibility modes are designed as drop-in replacements but incur additional overhead. The repository reports throughput of up to roughly 1,000 times that of Hugging Face tokenizers in its benchmarks.

img2obj is a Codex plugin that reconstructs an object from an attached image, screenshot, or local image path as a code-only, procedural Three.js model. It first validates the reference, then plans an ObjectSculptSpec covering the component hierarchy, geometry, materials, pivots, sockets, motion requirements, and visual priorities. The model is built through blockout, form, look-development, and interaction phases; browser renders are compared with the source image, with quality evidence and approval required before advancing. The plugin generates procedural Three.js geometry rather than extracting or downloading a mesh. It supports hard-surface and organic assets, vegetation, fabric, glass, hair or fur, emissive elements, and decals; can define animation-ready parent-child relationships, detachable parts, pivots, and sockets; and can produce reference-derived PBR evidence such as palette, roughness, height, normal, and ambient-occlusion maps. It is intended for stylized props, mechanical objects, plants, scene assets, and interactive models, not photogrammetry, exact mesh extraction, or guaranteed production-ready geometry from a single image. The repository requires Codex with local plugin support, Python 3.10 or newer, and a browser project using Three.js.