Vidu
Shengshu AI
The try panel will be available when this model launches.
Coming Soon
This model is not yet available. Subscribe to get notified when it launches.
Specifications
Pricing
TBD — pricing not yet announced
Coming soon
Vidu is the flagship video generation model from Shengshu AI (生数科技), a Beijing-based AI research company with deep roots in character animation and generative media. What sets Vidu apart from the crowded field of image-to-video models is its unique hybrid architecture that combines video diffusion generation with character animation techniques — enabling persistent visual identity across all frames of a clip. This makes Vidu particularly powerful for animated characters, brand mascots, and any use case where a specific character must remain visually locked throughout the video.
Capabilities
Vidu's core technical contribution is identity-preserving video synthesis: the model maintains a character's facial features, clothing design, colour palette, and body proportions with high fidelity even through dynamic actions and perspective changes. This capability is rare in AI video models, which typically show progressive drift in character appearance over longer clips. Vidu supports three aspect ratios and generates at up to 1080p, with clip durations up to 8 seconds — sufficient for social media content, game cinematics, and animated advertising spots.
Best Practices
Supply a clean, front-facing character reference image with minimal background clutter and consistent lighting to help Vidu build a stable identity representation. For stylised characters, use the original artwork or a rendered turntable frame as your input rather than a photo of a costume or real person. In your motion prompt, describe actions using animation vocabulary: "character waves cheerfully and jumps, landing with knees bent, eyes wide and mouth open in a smile" gives Vidu clear animation beats to follow. Avoid prompts that require the character to move off-screen and re-enter, as re-entry sequences are more prone to identity drift.
Frequently Asked Questions
How does Vidu maintain character consistency across frames?
Vidu is built on Shengshu AI's research into character representation and identity-preserving video synthesis. Unlike standard video diffusion models that process the input image as a single conditioning frame, Vidu encodes the character's visual identity into a persistent latent representation that constrains every generated frame — preventing the drift in appearance, clothing, and body proportions that affects most image-to-video models over longer clips.
What types of characters does Vidu animate best?
Vidu performs strongest on stylised characters — cartoon mascots, illustrated avatars, game characters, and brand anthropomorphics — where precise line art and colour consistency matter most. It also handles realistic human portraits well, particularly for action sequences where the body needs to move dynamically while maintaining recognisable facial identity.
When will Vidu be available on Genace?
Shengshu AI is expanding its international API access programme. Genace is working to establish a direct integration and will notify waitlist members as soon as Vidu is available on the platform.
Related Models
Kling 2.0
Kuaishou
Animate any image into a professional-grade video with Kling 2.0 by Kuaishou. Purpose-built for commercial portrait, product, and scene animation with support for Chinese prompts, 1080p output, and up to 10 seconds per clip.
Hailuo
MiniMax
Hailuo by MiniMax is a leading Chinese AI video model specialising in human portrait animation with accurate lip sync, natural facial expressions, and fluid body motion. Join the Genace waitlist to be among the first to try it via API.
Seedance 2.0
ByteDance
Transform static images into dynamic videos with Seedance 2.0 by ByteDance. Generate high-quality 720p/1080p videos up to 10 seconds with smooth motion and cinematic quality.