HiDream.ai · model guide

HiDream-O1-Video-1.0 Guide

New Sep 2026 HiDream model; current public API is image-conditioned with dynamic or fixed 10s output. This page connects the model data to working GenVideoKit prompt, image-to-video, comparison and cost tools.

Prompting strategy

Describe the reference state, intended physical action, camera motion, environment response and audiovisual result. Emphasize physical plausibility, character consistency and cause-and-effect. Keep the requested transformation bounded so the source identity does not drift unintentionally.

Capabilities

Image → videoReferencesNative audio

No stable flat reference price is stored; use your own provider/subscription rate in the calculator.