The video model just learned physics. hidream's o1-video-1.0, out oct 11, co-models text and video…
the video model just learned physics. hidream's o1-video-1.0, out oct 11, co-models text and video so scenes keep physical consistency and natural pacing.
the storyboard now plans the timeline itself.
Context
Verified event date: HiDream.ai announced HiDream-O1-Video-1.0, a native omnimodal video model built for physical consistency, on Sep 17, 2026 (press release; AI Stack Current dates its page Sep 15). It takes text, image and video inputs and generates 1080p videos of 5 to 20 seconds with natively synchronized audio.
AlphaSignal says it debuted at No. 6 on the Artificial Analysis image-to-video with audio leaderboard at Elo 1,175 and is priced at $5.80 per minute through the HiHarness API.
The model name, the physical consistency focus and the joint handling of text, image, video and audio match HiDream's release. The post says 'out oct 11'; the sources read date the launch to Sep 15 to 17, 2026. 'Co-models text and video' is the author's wording for a model described as native omnimodal. 'The storyboard now plans the timeline itself' is the author's, though the sources say the model chooses clip duration.
'the video model just learned physics' is the author's opinion.
Related work
- HiDream press release: HiDream-O1-Video-1.0 ↗Sep 17, 2026.
- AI Stack Current: HiDream-O1-Video-1.0 ↗Sep 15, 2026.
- AlphaSignal: HiDream-O1-Video-1.0 debuts at No. 6 ↗Leaderboard debut.
Watch next
- Check whether an Oct 11 update or new version of the model shipped.
Sources
- HiDream press release, Sep 17, 2026newsroom.xpr.media
- AI Stack Current, Sep 15, 2026aistackcurrent.com
- AlphaSignal, HiDream leaderboard debutalphasignal.ai
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 11 October 2026 at 11:53 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →