Cosmos physics-reasoning experiments (personal backup)
Personal working backup of code and experiment artifacts for a project built on NVIDIA/cosmos and NVIDIA/cosmos-framework, exploring physics/temporal reasoning and self-correction with video generation (LoRA fine-tuning, best-of-N sampling, physics-IQ style evaluation, etc.).
This is a private working snapshot, not an official release.
What's in this repo
code/cosmos/ # clone of NVIDIA/cosmos (cookbooks) + output/ (this
# project's scripts, LoRA adapters, generated videos,
# logs, analysis for physics/reasoning experiments)
code/cosmos-framework/ # unmodified clone of NVIDIA/cosmos-framework (training
# framework dependency, used via nvidia/Cosmos3-Nano)
experiments/ # working directories referenced by code/cosmos/output/*
# scripts (LoRA checkpoints, precompute caches, generated
# samples for each experiment: bon*, gate1*, m1_*,
# stage1_*, stage2_*, s2_*, ttr3*_*, emph*, overflow*,
# rollout_held4*)
env/ # pip freeze / uv pip freeze for the two envs used
# (cosmos3: python3.13 uv venv, cosmos-fw: python3.13 uv venv)
Not included (deliberately)
nvidia/Cosmos3-Nanobase model weights: loaded viafrom_pretraineddirectly from the Hugging Face Hub at runtime, not stored locally.ckpt/videocon_physics(14GB) andvjepa2_ckpt/vitl.pt(4.8GB): publicly downloadable evaluator/encoder checkpoints (VideoCon-Physics, VJEPA2 ViT-L), same artifacts used in the companion VideoREPA project.physicsiq/(20GB): the public Physics-IQ benchmark dataset, used read-only for evaluation — not re-hosted here.
Environment
env/requirements_cosmos3.txt and env/requirements_cosmos-fw.txt are captured
via pip freeze / uv pip freeze from the two uv-managed Python 3.13 venvs used
for this project. Recreate with:
uv venv --python 3.13 .venv-cosmos3 && uv pip install -r env/requirements_cosmos3.txt
uv venv --python 3.13 .venv-cosmos-fw && uv pip install -r env/requirements_cosmos-fw.txt
code/cosmos-framework's own pyproject.toml / uv.lock is the authoritative
dependency spec for that framework; the requirements dump above is a snapshot of
what was actually installed.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support