{"adoption": {"forks": 94, "observed_at": "2026-08-28T04:05:28.682316+00:00", "stars": 1731}, "canonical_url": "https://ross.abutalabs.com/products/cosmos-tokenizer", "card": {"archived": true, "artifact_type": "library", "description": "A suite of image and video neural tokenizers", "domain": ["deep-learning", "machine-learning", "computer-vision", "image-processing", "artificial-intelligence"], "enriched": true, "function": ["machine-learning", "deep-learning", "image-processing", "video-processing", "serialization"], "health_score": 10, "homepage": "https://research.nvidia.com/labs/dir/cosmos-tokenizer", "language": "Jupyter Notebook", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["NVIDIA/Cosmos-Tokenizer"], "name": "NVIDIA/Cosmos-Tokenizer", "platform": ["python", "cross-platform"], "pushed_at": "2025-02-11T05:49:24+00:00", "repo": "NVIDIA/Cosmos-Tokenizer", "stars": 1731, "tags": ["tokenization", "diffusion-models", "transformers", "video-foundation-models", "latent-compression", "nvidia", "physical-ai", "video", "gpu", "linux"], "topics": ["diffusion", "tokenization", "transformers"], "urls": [], "use_cases": ["tokenize videos into discrete tokens for autoregressive transformer training", "compress images into continuous latents for diffusion model training", "build physical AI or world model pipelines with efficient visual tokenization", "reduce video data storage and compute costs with high compression tokenization", "preprocess visual datasets for large multimodal generative AI models"], "what_it_is": "NVIDIA Cosmos Tokenizer is a suite of neural tokenizers for images and videos that convert visual data into continuous latents or discrete tokens for use in diffusion or auto-regressive transformer models. It achieves high spatial and temporal compression (up to 2048x total) and serves as a core component of the NVIDIA Cosmos video foundation model platform.", "when_to_avoid": ["you need a general-purpose image/video codec for playback or archival rather than ML tokenization", "you lack GPU resources, as the models require GPU inference", "you need active development here - the repo is read-only and moved to NVIDIA/Cosmos"], "when_to_choose": ["you need state-of-the-art image/video tokenization for training diffusion or autoregressive generative models", "you are building on the NVIDIA Cosmos video foundation model ecosystem", "you need extreme compression of visual data (up to 2048x) for scalable model training"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/cosmos-tokenizer", "repo": "NVIDIA/Cosmos-Tokenizer", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.682316+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:31:41.226120+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3b2d7d50355ed83ca989bd21314aefa46602f6302424e6dca6b781357d39743d", "fetched_at": "2026-08-28T04:05:28.682316+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/Cosmos-Tokenizer"}, {"content_hash": "f700d88d9bdb7909c6b3749374287c4efdbe0b03c54bd56e4fdd11c4b4f7e6f7", "fetched_at": "2026-08-29T11:08:25.467193+00:00", "kind": "homepage", "missing": false, "url": "https://research.nvidia.com/labs/dir/cosmos-tokenizer"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.682316+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:31:41.226120+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3b2d7d50355ed83ca989bd21314aefa46602f6302424e6dca6b781357d39743d", "fetched_at": "2026-08-28T04:05:28.682316+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/Cosmos-Tokenizer"}, {"content_hash": "f700d88d9bdb7909c6b3749374287c4efdbe0b03c54bd56e4fdd11c4b4f7e6f7", "fetched_at": "2026-08-29T11:08:25.467193+00:00", "kind": "homepage", "missing": false, "url": "https://research.nvidia.com/labs/dir/cosmos-tokenizer"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:31:41.226120+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3b2d7d50355ed83ca989bd21314aefa46602f6302424e6dca6b781357d39743d", "fetched_at": "2026-08-28T04:05:28.682316+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/Cosmos-Tokenizer"}, {"content_hash": "f700d88d9bdb7909c6b3749374287c4efdbe0b03c54bd56e4fdd11c4b4f7e6f7", "fetched_at": "2026-08-29T11:08:25.467193+00:00", "kind": "homepage", "missing": false, "url": "https://research.nvidia.com/labs/dir/cosmos-tokenizer"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.682316+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.682316+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.682316+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:31:41.226120+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3b2d7d50355ed83ca989bd21314aefa46602f6302424e6dca6b781357d39743d", "fetched_at": "2026-08-28T04:05:28.682316+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/Cosmos-Tokenizer"}, {"content_hash": "f700d88d9bdb7909c6b3749374287c4efdbe0b03c54bd56e4fdd11c4b4f7e6f7", "fetched_at": "2026-08-29T11:08:25.467193+00:00", "kind": "homepage", "missing": false, "url": "https://research.nvidia.com/labs/dir/cosmos-tokenizer"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.682316+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.682316+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:31:41.226120+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3b2d7d50355ed83ca989bd21314aefa46602f6302424e6dca6b781357d39743d", "fetched_at": "2026-08-28T04:05:28.682316+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/Cosmos-Tokenizer"}, {"content_hash": "f700d88d9bdb7909c6b3749374287c4efdbe0b03c54bd56e4fdd11c4b4f7e6f7", "fetched_at": "2026-08-29T11:08:25.467193+00:00", "kind": "homepage", "missing": false, "url": "https://research.nvidia.com/labs/dir/cosmos-tokenizer"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.682316+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.682316+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.682316+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:31:41.226120+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3b2d7d50355ed83ca989bd21314aefa46602f6302424e6dca6b781357d39743d", "fetched_at": "2026-08-28T04:05:28.682316+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/Cosmos-Tokenizer"}, {"content_hash": "f700d88d9bdb7909c6b3749374287c4efdbe0b03c54bd56e4fdd11c4b4f7e6f7", "fetched_at": "2026-08-29T11:08:25.467193+00:00", "kind": "homepage", "missing": false, "url": "https://research.nvidia.com/labs/dir/cosmos-tokenizer"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.682316+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.682316+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:31:41.226120+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3b2d7d50355ed83ca989bd21314aefa46602f6302424e6dca6b781357d39743d", "fetched_at": "2026-08-28T04:05:28.682316+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/Cosmos-Tokenizer"}, {"content_hash": "f700d88d9bdb7909c6b3749374287c4efdbe0b03c54bd56e4fdd11c4b4f7e6f7", "fetched_at": "2026-08-29T11:08:25.467193+00:00", "kind": "homepage", "missing": false, "url": "https://research.nvidia.com/labs/dir/cosmos-tokenizer"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:31:41.226120+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3b2d7d50355ed83ca989bd21314aefa46602f6302424e6dca6b781357d39743d", "fetched_at": "2026-08-28T04:05:28.682316+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/Cosmos-Tokenizer"}, {"content_hash": "f700d88d9bdb7909c6b3749374287c4efdbe0b03c54bd56e4fdd11c4b4f7e6f7", "fetched_at": "2026-08-29T11:08:25.467193+00:00", "kind": "homepage", "missing": false, "url": "https://research.nvidia.com/labs/dir/cosmos-tokenizer"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:31:41.226120+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3b2d7d50355ed83ca989bd21314aefa46602f6302424e6dca6b781357d39743d", "fetched_at": "2026-08-28T04:05:28.682316+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/Cosmos-Tokenizer"}, {"content_hash": "f700d88d9bdb7909c6b3749374287c4efdbe0b03c54bd56e4fdd11c4b4f7e6f7", "fetched_at": "2026-08-29T11:08:25.467193+00:00", "kind": "homepage", "missing": false, "url": "https://research.nvidia.com/labs/dir/cosmos-tokenizer"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:31:41.226120+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3b2d7d50355ed83ca989bd21314aefa46602f6302424e6dca6b781357d39743d", "fetched_at": "2026-08-28T04:05:28.682316+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVIDIA/Cosmos-Tokenizer"}, {"content_hash": "f700d88d9bdb7909c6b3749374287c4efdbe0b03c54bd56e4fdd11c4b4f7e6f7", "fetched_at": "2026-08-29T11:08:25.467193+00:00", "kind": "homepage", "missing": false, "url": "https://research.nvidia.com/labs/dir/cosmos-tokenizer"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 6, "longevity": 48, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 672, "days_push": 568, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}