Vidu Models

Vidu is Shengshu Technology's advanced AI image and video generation model suite, covering text-to-video, image-to-video, reference-to-video, start-end frame generation, text-to-image, reference-to-image, music video creation, short drama generation, and commercial ad video workflows. The collection brings together Vidu Q3, Q2, Q1, 2.0, and specialized creative models, giving creators and developers flexible tools for cinematic storytelling, social media content, product videos, branded campaigns, and scalable creative production.

Built for professional video creation, Vidu focuses on strong prompt understanding, smooth motion, stable subject consistency, cinematic camera control, and robust temporal coherence. It supports both general-purpose generation and scenario-specific workflows, from animating still images and generating videos from prompts to creating short dramas, music videos, and commercial advertising content.

Core Model Capabilities

Featured Scenario Models:

Vidu includes featured scenario models for specialized production workflows. vidu/drama is designed for short-form drama, episodic storytelling, emotionally expressive scenes, and character-focused narrative content. vidu/ad is built for commercial advertising workflows, helping create polished product showcases, brand videos, promotional creatives, and conversion-focused campaign assets. vidu/one-click-v2/mv transforms images and audio into dynamic music videos with camera movement and subtitle support, making it ideal for creator content, music promotion, social clips, and fast visual-audio production.

Text-to-Video Generation:

Generate cinematic videos directly from natural-language prompts with strong prompt adherence, coherent scene structure, controllable camera movement, and natural multi-character interactions.

Image-to-Video Generation:

Animate still images into dynamic video clips while preserving subject identity, composition, lighting, and visual style. Vidu's newer Q3 and Q2 models provide stronger motion quality, structural fidelity, and cinematic realism for more polished outputs.

Reference-to-Video Generation:

Create videos guided by reference images or visual inputs, helping maintain character identity, object appearance, wardrobe consistency, visual style, and scene continuity across generated clips.

Start-End Frame Video Generation:

Generate smooth motion between a defined starting frame and ending frame, making it useful for transitions, reveals, storyboard-based motion design, product shots, and controlled narrative progression.

Image Generation:

Create cinematic key visuals, posters, thumbnails, concept frames, and reference-guided still images from text prompts or multiple reference images.

Fast and Pro Workflows:

Choose newer Q3 models for stronger overall quality, Q2 Pro models for polished production assets, Turbo and Fast variants for rapid iteration, and earlier models for lightweight drafts or cost-efficient generation.

Production-Ready Video API:

Access Vidu models through scalable APIs for automated video generation, social media production, advertising pipelines, product content, creative testing, and commercial media workflows.

Vidu AI Models on WaveSpeedAI give creators and developers fast access to a complete AI video and image generation toolkit with flexible pricing, scalable API access, and production-ready creative quality.