HiDream's vivago R1 AI video agent goes global
The Beijing lab's agent joins script, storyboard and edit in one chat workflow, and HiDream says it plans to add a model ranked No. 4 for image-to-video.

Key takeaways
- HiDream.ai made vivago R1, its AI video creation agent, available globally on October 7, 2026, with videos of up to five minutes in one production workflow.
- vivago R1 combines scriptwriting, storyboarding, video generation and editing in one workflow, with a command-line interface for developers and AI agents.
- HiDream plans to add HiDream-O1-Video-1.0, which it says ranked No. 4 on the Artificial Analysis Image to Video Leaderboard (With Audio), to vivago R1 in an upcoming update.
- HiDream-O1-Video-1.0 generates 1080p video with natively synchronized audio, according to the launch announcement.
HiDream.ai has made vivago R1, its AI video creation agent, available worldwide, the Beijing lab said on October 7.
The announcement came in a release distributed by Newsfile Corp., which describes R1 as a production agent that carries a project from a written brief to a finished video rather than assembling it from separately generated clips.
R1 puts scriptwriting, storyboarding, video generation and editing into one chat-based workflow. HiDream says a user can produce videos of up to five minutes in a single production workflow and extend a project through additional rounds of creation. Creators describe an idea in natural language, supply reference materials and refine the result through conversation.
The agent runs on a system of models. A lead agent reads the brief and builds a production plan, while specialized agents handle scripts, storyboards, characters, environments and audio. HiDream's HD-AgentOS coordinates the work and the context the tasks share. A library called SkillHub offers reusable workflows for jobs such as a product ad or a narrative short. The release lists creator examples that include a story of nearly five minutes inspired by Journey to the West and an ad about a designer who captures ideas with a red foldable phone.
R1 keeps approved assets for later projects and holds characters, locations, props and voices steady across shots, so serialized episodes can carry the same cast forward. HiDream exposes the same capabilities through a command-line interface, letting developers and compatible AI agents start generations, process media and manage production jobs from scripts or task queues. The release notes that availability of specific integrations may vary by platform.
HiDream plans to add HiDream-O1-Video-1.0, its native omnimodal video model, to vivago R1 in an upcoming update. According to the launch announcement, the model ranked No. 4 on the Artificial Analysis Image to Video Leaderboard (With Audio) and No. 7 on the Arena.ai Image-to-Video leaderboard at launch. HiDream-O1-Video-1.0 generates 1080p video with natively synchronized audio and is built to improve how it handles multimodal instructions, physical behavior and audiovisual coherence.
If those leaderboard placements hold and the model lands in R1, creators would get image-to-video generation with native audio inside an agent that already manages structure and continuity, a pairing most clip generators leave to the user.
Watch the launch video below.
vivago R1 is available globally at vivago.ai, where new accounts start with 30 free credits. HiDream also released an updated version of Gouda, its China-focused product.
Sources
- newsfilecorp.com - launch announcement, specs, leaderboard rankings, availability
- vivago.ai - product availability and new-account credits