Files
2026-06-07 20:43:31 -07:00

2.2 KiB

Vidu

Vidu is a video generation API developed by ShengShu Technology. It supports text-to-video, image-to-video, reference-to-video with multi-entity consistency, and start-end frame interpolation. Vidu is known for fast generation speeds (as low as 10 seconds) and strong anime-style output.

Model Variants

Vidu 2.0

  • Extended 8-second video generation at up to 1080p
  • Text-to-video and image-to-video modes
  • First and last frame control for transitions
  • Available via the Vidu API and third-party platforms

Vidu Q1

  • Reference-to-video with multi-entity consistency
  • Supports up to 7 reference images with semantic understanding
  • Infers missing elements from text prompts and reference context
  • Generates coherent scenes combining multiple characters, objects, and environments

Vidu Q2

  • Optimized for quality and speed balance
  • Supports 6-8 second generation at up to 1080p
  • 1080p image generation included in higher tiers

Vidu Q3

  • Latest generation model with improved output quality
  • Available through the Vidu platform and API

Key Features

  • Ultra-fast inference (videos generated in as few as 10 seconds)
  • Multi-entity consistency across characters, objects, and scenes
  • First and last frame control for precise transitions
  • Superior anime and 2D animation quality
  • Up to 1080p resolution output with multiple aspect ratios
  • Optimized scene templates for interactive effects and e-commerce

Hardware Requirements

  • Cloud API only; no local hardware required
  • Accessed via platform.vidu.com or third-party API providers
  • Credit-based pricing with free tier available

Common Use Cases

  • Anime and 2D animation series production
  • E-commerce product video creation
  • Social media content (TikTok, Reels, Shorts)
  • Reference-based multi-character storytelling
  • Marketing and advertising videos
  • Start-end frame transitions and morphing effects

Key Parameters

  • prompt: Text description of desired video content
  • image_url: Source image for image-to-video generation
  • duration: Video length (4-8 seconds depending on model)
  • resolution: Output resolution (720p or 1080p)
  • style: Visual style selection (realistic or animated)
  • movement_amplitude: Controls intensity of motion in output