localai-org/kimodo.cpp

Nix is optional and provides these dependencies reproducibly:

nix develop path:. --command cmake --preset debug
nix develop path:. --command cmake --build --preset debug

For sanitizer work:

nix develop path:. --command cmake --preset asan-ubsan
nix develop path:. --command cmake --build --preset asan-ubsan
nix develop path:. --command env \
  LD_LIBRARY_PATH="$PWD/build/asan-ubsan/ggml/src:$PWD/build/asan-ubsan/ggml/src/ggml-vulkan:$LD_LIBRARY_PATH" \
  ASAN_OPTIONS=detect_leaks=0:abort_on_error=1 UBSAN_OPTIONS=print_stacktrace=1 \
  ctest --preset asan-ubsan --output-on-failure

Leak detection is disabled because Vulkan loader/driver allocations are global to the process. The GGUF parser fuzzer requires Clang.

API

include/kimodo/kimodo_capi.h is the C API. Model loading checks the motion GGUF and text bundle before inference. Use kimodo_generate_embedding for 4096 F32 values or kimodo_generate for text. Both return the selected model's root translations and local XYZW rotations; query the joint count from the result rather than assuming a fixed skeleton.

Demo

After building the debug preset and downloading the native GGUF bundle:

go run ./demo -addr 0.0.0.0:8094

Open http://localhost:8094. The left sidebar contains the prompt and a persistent history; choosing a previous animation restores its prompt for a new generation. Every successful animation also writes a standalone animation.glb beside its raw streams, for example demo-output/<animation-id>/animation.glb. It contains the selected animated node hierarchy (no mesh), ready to copy into a Three.js project. It is also available from /api/animations/<animation-id>/animation.glb while the demo is running.

Weights

Ready-to-run native GGML weights are published under the Hugging Face LocalAI-io organisation (not GitHub's localai-org). The reusable Llama-3-Kimodo-GGML text encoder is separate from the four redistributable motion repositories, each of which preserves a one-to-one relationship to its NVIDIA upstream:

• Kimodo-SOMA-RP-v1.1-GGML
• Kimodo-SOMA-SEED-v1.1-GGML
• Kimodo-G1-RP-v1-GGML
• Kimodo-G1-SEED-v1-GGML

Download one or repeat --model to install several:

scripts/download_gguf_weights.sh --output "$PWD" \
  --model soma-rp-v1.1 --model g1-rp-v1

The installer verifies each published manifest and SHA-256 hashes. Use --motion-only when supplying a precomputed 4096-float LLM2Vec embedding. SMPL-X RP is deliberately absent from the published-weight installer: its internal-R&D licence prohibits distributing derivative models, so it must be converted locally after the user obtains the upstream checkpoint under its gated terms.

The text bundle includes converted Meta Llama 3 material and retains its separate terms. Review every selected model card before downloading or redistributing.

License

The C++ port and its original tooling are licensed under Apache-2.0; see LICENSE. GGML and the model weights retain their respective licences.

The SMPL-X warning is about NVIDIA's trained Kimodo checkpoint, not the mere fact that its output uses an SMPL-X-shaped 22-joint hierarchy. Converting that checkpoint to GGUF is a new runtime representation of the same weights and does not replace its licence. Skeleton names, parent links, and the Apache-2.0 port source do not by themselves make the SOMA or G1 checkpoints non-commercial. The SMPL-X Hugging Face metadata, model card, and access terms identify the internal-R&D licence; treat those restrictive terms as controlling even though an apparently inconsistent LICENSE file has also appeared in that upstream repository.

Regenerating the bundle

This is only needed to reproduce a conversion. The SMPL-X checkpoint and Llama base model are gated. After accepting their Hugging Face licences and authenticating, download the exact revisions and hash manifests with:

nix develop path:. --command hf auth login
scripts/download_weights.sh --output "$PWD/models" --with-text \
  --model smplx-rp-v1 --model soma-rp-v1.1 --model soma-seed-v1.1 \
  --model g1-rp-v1 --model g1-seed-v1

Convert the local LLM2Vec model to the native component bundle with:

nix develop path:. --command scripts/convert_llm2vec_bundle.sh \
  "$PWD/models/llama3-8b-instruct-base" "$PWD/generated/llm2vec-text-bundle"

Validate a prospective release without network access, then explicitly upload it from an account allowed to publish to LocalAI-io:

nix develop path:. --command python scripts/publish_gguf.py --component motion \
  --motion-model soma-rp-v1.1
nix develop path:. --command python scripts/publish_gguf.py --component motion \
  --motion-model soma-rp-v1.1 --upload --confirm-upstream-licences
nix develop path:. --command python scripts/publish_gguf.py --component text \
  --upload --confirm-upstream-licences