Wire flash
HiDream releases O1-Video-1.0 model, debuts at #6 on AI image-to-video leaderboard
Editorial responsibility
- No named human review is recorded for this page.
- Source reporting is collected, normalized, translated or condensed automatically when needed.
- Automatically published source-backed update
HiDream has released HiDream-O1-Video-1.0, a new native omnimodal video model focused on generative AI and physical consistency. The model debuted at #6 on the Artificial Analysis Image to Video with Audio Leaderboard, positioned just behind Dreamina Seedance 2.0 720p and in a close group with MiniMax H3, Vidu Q4 Preview, and Gemini Omni Flash, ahead of Wan 3.0. It generates 1080p videos lasting 5 to 20 seconds with natively synchronized audio, with duration set by the scene rather than fixed in advance. The model is priced at $5.80 per minute of 1080p video with audio (approximately $0.10 per second) on the HiHarness API. It is available via the HiHarness API and in vivago R1 Studio.
Source report
HiDream-O1-Video-1.0 is the latest video model from HiDream, a company focused on "generative AI and native omnimodal world models." The model is positioned as a native omnimodal video solution built for physical consistency.
Key Features
- Generates 1080p videos ranging from 5 to 20 seconds
- Features natively synchronized audio
- Video duration is determined by the scene, not fixed in advance
Leaderboard Performance
In the Artificial Analysis Video Arena, HiDream-O1-Video-1.0 ranks #6 in the Image to Video with Audio category. It sits:
- Just behind Dreamina Seedance 2.0 720p
- In a close group with MiniMax H3, Vidu Q4 Preview, and Gemini Omni Flash
- Ahead of Wan 3.0
Pricing
HiDream-O1-Video-1.0 is priced at $5.80 per minute of 1080p video with audio (approximately $0.10 per second) via the HiHarness API.
Availability
The model is available through:
- HiHarness API
- vivago R1 Studio
Congratulations to @HiDream_AI on the release!
See below for example outputs of HiDream-O1-Video-1.0 in the Artificial Analysis Video Arena.
Source
ArtificialAnlysNeutral / independent