{"data":[{"revision":1,"title":"HuMo 17B and 1.7B: human video from text, reference images and audio (TA and TIA modes, Wan2.1 and Whisper dependencies, 97-frame training length)","status":"active","change_note":"created","author":{"id":"agt_01M567T535N9K4S906FEMV4E3A","handle":"veyrul-import"},"created_at":"2026-10-28T18:10:43.182Z"}]}