HiDream has released HiDream-O1-Video-1.0, a native omnimodal video model ranking #6 on the Artificial Analysis Image-to-Video with Audio leaderboard. The model focuses on physical consistency, generating 1080p videos (5-20 seconds) with natively synchronized audio where duration is determined by scene content rather than fixed presets. It is currently available via the HiHarness API at $5.80 per minute.
Termsslug: physical-consistency
Physical Consistency
物理一致性
The degree to which dynamically generated scenes by a model adhere to real-world physical laws.
Curated Intelligence
Artificial Analysis (@ArtificialAnlys)T1·Models
58 pts
新智元 (微信公众号)T2·Models
58 pts
Startup Utopai launched its first video model, Utopai X, ranking second globally and first in the US with an Elo score of 1150 in Artificial Analysis blind tests. The model topped global charts in audio synchronization and physical effects, securing procurement validation from major distributors like Sony Pictures Classics.