{"adoption": {"forks": 94, "observed_at": "2026-08-28T04:04:56.319018+00:00", "stars": 1514}, "canonical_url": "https://ross.abutalabs.com/products/describe-anything", "card": {"archived": false, "artifact_type": "library", "description": "[ICCV 2025] Implementation for Describe Anything: Detailed Localized Image and Video Captioning", "domain": ["computer-vision", "large-language-models", "artificial-intelligence", "image-processing"], "enriched": true, "function": ["machine-learning", "computer-vision", "image-processing", "video-processing", "nlp"], "health_score": 37, "homepage": "https://describe-anything.github.io/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["NVlabs/describe-anything"], "name": "NVlabs/describe-anything", "platform": ["python", "windows"], "pushed_at": "2025-06-26T03:57:51+00:00", "repo": "NVlabs/describe-anything", "stars": 1514, "tags": ["vision-language-model", "region-captioning", "image-captioning", "video-captioning", "segmentation", "gradio-demo", "benchmark", "iccv-2025", "multimodal", "video", "linux", "macos", "gpu"], "topics": ["large-multimodal-models", "vision-language-model", "describe-anything", "detailed-localized-captioning"], "urls": [], "use_cases": ["generate detailed captions for a specific region of an image", "describe objects in a video by annotating one frame", "caption image regions using masks from SAM", "evaluate localized captioning models with DLC-Bench", "build an app that describes clicked or boxed image areas", "run a local gradio demo for region-based image description"], "what_it_is": "Describe Anything Model (DAM) is a vision-language model that generates detailed descriptions of user-specified regions in images and videos, indicated via points, boxes, scribbles, or masks. The repository provides the model implementation, Gradio demos, SAM integration, and the DLC-Bench evaluation benchmark.", "when_to_avoid": ["you only need simple whole-image captioning without region specification", "you lack a GPU or cannot run large multimodal models locally", "you need a production-ready hosted API rather than a research codebase"], "when_to_choose": ["you need fine-grained, localized image or video descriptions rather than whole-image captions", "you want a research-grade vision-language model with a permissive Apache-2.0 license", "you need a benchmark for evaluating detailed localized captioning"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/describe-anything", "repo": "NVlabs/describe-anything", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:56.319018+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:32:11.457163+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13e2a66513429eda8348a9a1d01110511d05b37faca56261dba018a61f51463c", "fetched_at": "2026-08-28T04:04:56.319018+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVlabs/describe-anything"}, {"content_hash": "3f9b27456586dff52f16c2408920e7c06facbf959edb68d96ec3e132fcba0e0d", "fetched_at": "2026-08-29T11:35:46.592583+00:00", "kind": "homepage", "missing": false, "url": "https://describe-anything.github.io/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:56.319018+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:32:11.457163+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13e2a66513429eda8348a9a1d01110511d05b37faca56261dba018a61f51463c", "fetched_at": "2026-08-28T04:04:56.319018+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVlabs/describe-anything"}, {"content_hash": "3f9b27456586dff52f16c2408920e7c06facbf959edb68d96ec3e132fcba0e0d", "fetched_at": "2026-08-29T11:35:46.592583+00:00", "kind": "homepage", "missing": false, "url": "https://describe-anything.github.io/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:32:11.457163+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13e2a66513429eda8348a9a1d01110511d05b37faca56261dba018a61f51463c", "fetched_at": "2026-08-28T04:04:56.319018+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVlabs/describe-anything"}, {"content_hash": "3f9b27456586dff52f16c2408920e7c06facbf959edb68d96ec3e132fcba0e0d", "fetched_at": "2026-08-29T11:35:46.592583+00:00", "kind": "homepage", "missing": false, "url": "https://describe-anything.github.io/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:56.319018+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:56.319018+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:56.319018+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:32:11.457163+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13e2a66513429eda8348a9a1d01110511d05b37faca56261dba018a61f51463c", "fetched_at": "2026-08-28T04:04:56.319018+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVlabs/describe-anything"}, {"content_hash": "3f9b27456586dff52f16c2408920e7c06facbf959edb68d96ec3e132fcba0e0d", "fetched_at": "2026-08-29T11:35:46.592583+00:00", "kind": "homepage", "missing": false, "url": "https://describe-anything.github.io/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:56.319018+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:56.319018+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:32:11.457163+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13e2a66513429eda8348a9a1d01110511d05b37faca56261dba018a61f51463c", "fetched_at": "2026-08-28T04:04:56.319018+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVlabs/describe-anything"}, {"content_hash": "3f9b27456586dff52f16c2408920e7c06facbf959edb68d96ec3e132fcba0e0d", "fetched_at": "2026-08-29T11:35:46.592583+00:00", "kind": "homepage", "missing": false, "url": "https://describe-anything.github.io/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:56.319018+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:56.319018+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:56.319018+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:32:11.457163+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13e2a66513429eda8348a9a1d01110511d05b37faca56261dba018a61f51463c", "fetched_at": "2026-08-28T04:04:56.319018+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVlabs/describe-anything"}, {"content_hash": "3f9b27456586dff52f16c2408920e7c06facbf959edb68d96ec3e132fcba0e0d", "fetched_at": "2026-08-29T11:35:46.592583+00:00", "kind": "homepage", "missing": false, "url": "https://describe-anything.github.io/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:56.319018+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:56.319018+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:32:11.457163+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13e2a66513429eda8348a9a1d01110511d05b37faca56261dba018a61f51463c", "fetched_at": "2026-08-28T04:04:56.319018+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVlabs/describe-anything"}, {"content_hash": "3f9b27456586dff52f16c2408920e7c06facbf959edb68d96ec3e132fcba0e0d", "fetched_at": "2026-08-29T11:35:46.592583+00:00", "kind": "homepage", "missing": false, "url": "https://describe-anything.github.io/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:32:11.457163+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13e2a66513429eda8348a9a1d01110511d05b37faca56261dba018a61f51463c", "fetched_at": "2026-08-28T04:04:56.319018+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVlabs/describe-anything"}, {"content_hash": "3f9b27456586dff52f16c2408920e7c06facbf959edb68d96ec3e132fcba0e0d", "fetched_at": "2026-08-29T11:35:46.592583+00:00", "kind": "homepage", "missing": false, "url": "https://describe-anything.github.io/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:32:11.457163+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13e2a66513429eda8348a9a1d01110511d05b37faca56261dba018a61f51463c", "fetched_at": "2026-08-28T04:04:56.319018+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVlabs/describe-anything"}, {"content_hash": "3f9b27456586dff52f16c2408920e7c06facbf959edb68d96ec3e132fcba0e0d", "fetched_at": "2026-08-29T11:35:46.592583+00:00", "kind": "homepage", "missing": false, "url": "https://describe-anything.github.io/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:32:11.457163+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "13e2a66513429eda8348a9a1d01110511d05b37faca56261dba018a61f51463c", "fetched_at": "2026-08-28T04:04:56.319018+00:00", "kind": "readme", "missing": false, "url": "https://github.com/NVlabs/describe-anything"}, {"content_hash": "3f9b27456586dff52f16c2408920e7c06facbf959edb68d96ec3e132fcba0e0d", "fetched_at": "2026-08-29T11:35:46.592583+00:00", "kind": "homepage", "missing": false, "url": "https://describe-anything.github.io/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 28, "longevity": 36, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 516, "days_push": 433, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}