{"passport":{"slug":"univid","display_name":"UniVid","model_type":"multimodal","parameter_count":null,"context_window":null,"claimed_developer":"UniVid: Pyramid Diffusion Model for High Quality Video Generation","confirmed_developer":null,"developer_confirmed_at":null,"developer_source":null,"first_appeared_at":"2026-03-20T12:31:23.761706+00:00","first_appeared_on":"rss_pipeline","status":"confirmed","availability":null,"deployment_status":"not_deployed","availability_scope":null,"gate":1,"eu_ai_act":"GPAI","regulatory_status":{"eu_ai_act":"GPAI"},"open_source":null,"weights_available":null,"license":null,"provenance_chain":[],"parent_model":null,"model_family":null,"superseded_by":null,"supersedes":[],"recommended_replacement":null,"product_links":null},"events":[{"event_type":"first_appearance","event_date":"2026-03-20T12:31:23.761706+00:00","title":"First recorded in AI news","detail":"UniVid is a unified video generation model that can generate temporally coherent frames by using a text prompt and a reference image as inputs. It scales up a pre-trained text-to-image diffusion model and introduces temporal-pyramid cross-frame spatial-temporal attention modules and convolutions to support bimodal control.","source_url":"https://arxiv.org/abs/2603.13739","source_name":"ArXiv AI"}],"delta":{"days_unattributed":111,"claimed_developer":"UniVid: Pyramid Diffusion Model for High Quality Video Generation","confirmed_developer":null,"match":false}}