{"name":"anymove","repo":"patch-gg/anymove","url":"https://midorreal.com/project/patch-gg-anymove","repository":"https://github.com/patch-gg/anymove","description":"Motion capture for any creature from one AI video: two cameras in one frame, a DINOv2 joint reader, the rig fitted in both views, a GLB out.","facts":{"license":{"value":"Apache-2.0","source":"https://github.com/patch-gg/anymove","checked":"22 Nov 2026"},"language":{"value":"Python","source":"https://github.com/patch-gg/anymove","checked":"22 Nov 2026"},"homepage":{"value":"https://patch.gg","source":"https://patch.gg","checked":"22 Nov 2026"},"last_release":{"value":"examples-v1, 27 Oct 2026","source":"https://github.com/patch-gg/anymove/releases","checked":"22 Nov 2026"},"releases":{"value":"1","source":"https://github.com/patch-gg/anymove/releases","checked":"20 Nov 2026"},"contributors":{"value":"3","source":"https://github.com/patch-gg/anymove/graphs/contributors","checked":"20 Nov 2026"},"archived":{"value":"no","source":"https://github.com/patch-gg/anymove","checked":"22 Nov 2026"}},"stars":654.0,"writeup":{"what_it_is":"anymove is a motion capture pipeline that turns one AI-generated video into an animation for a rigged creature. It films the creature from a front view and a side view in one frame, trains a joint reader on that creature, fits the rig to the joints in both views, and exports a GLB file.","audience":"Game developers and creators who want animations for custom, non-humanoid creatures.","claims":[{"kind":"broad","claim":"Produces animation for any creature, including wings, tails and eight legs","excerpt":"anymove turns one AI video into an animation for any rigged creature, wings, tails and eight legs included.","status":"too_broad"},{"kind":"specific","claim":"Costs about $3 for a usable move","excerpt":"about $3 for a usable move, all in.","status":"not_checked"},{"kind":"specific","claim":"Exports the animation as a GLB file","excerpt":"the rig is fitted to those joints frame by frame and exported as a GLB.","status":"not_checked"},{"kind":"specific","claim":"Reader's average joint miss falls from 40 px to 6 px","excerpt":"its average miss falls from 40 px to 6 px.","status":"not_checked"},{"kind":"specific","claim":"Requires an NVIDIA card with 12 GB of memory to train a reader","excerpt":"an NVIDIA card (12 GB to train a reader, 24 GB is safer)","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-14"},"why_now":null,"owner_supplied":null,"score":{"verdict":"mid","hype":61,"reality":42,"gap":19,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T07:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-10-27T08:12:11+00:00","text":"Latest release examples-v1","source":"https://github.com/patch-gg/anymove/releases"},{"date":"2026-10-27T08:00:42+00:00","text":"Repository created","source":"https://github.com/patch-gg/anymove"}],"cite":"anymove is a GitHub project at https://github.com/patch-gg/anymove written mainly in Python, described there as \"Motion capture for any creature from one AI video: two cameras in one frame, a DINOv2 joint reader, the rig fitted in both views, a GLB out\".","attribution":"Data from Mid or Real, https://midorreal.com/project/patch-gg-anymove, checked 22 November 2026. Attribution with a link is required.","still_real":null}