88Z AI, 6 July — Shengshu Technology unveiled the Vidu S1 real-time interactive model at the 2026 Global Digital Economy Conference. The model supports voice-controlled video generation and unlimited continuous interaction, featuring 540P resolution and 25 FPS. Users can create personalized characters such as humans, anime figures, or pets by uploading a single image without additional modeling training.
At a glance
- Vidu S1 supports voice-controlled video direction and unlimited continuous interaction with 540P/25FPS quality.
- Users can generate personalized characters like humans or anime from a single image without modeling training.
The update
Shengshu Technology officially launched the Vidu S1 real-time interactive model at the 2026 Global Digital Economy Conference. This model features robust real-time interaction capabilities, allowing users to control video content direction via voice commands and supporting unlimited continuous interaction. Visually, Vidu S1 delivers up to 540P resolution and a smooth 25 FPS frame rate, ensuring clear and natural motion. Regarding character creation, Vidu S1 significantly lowers the barrier to entry. Users can quickly generate various personalized interactive characters, including humans, anime figures, or pets, by simply uploading a single image. The entire process requires no complex modeling or training steps, enabling instant conversion from static images to dynamic interactive characters and providing an efficient solution for digital content creation.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- 生数科技Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.