VIDU VIDEO MODELS
Vidu 2.0 model collection
Vidu 2.0 is a family of open-source diffusion-based video generation models designed by Shengshu Technology, trained on large-scale, high-quality datasets with human-aligned tuning. All three variants on WaveSpeedAI offer distinct entry points into controllable video synth
vidu/start-end-to-video-2.0
$0.2
Create dynamic videos using just the first and last frame images, enhanced with text descriptions for seamless storytelling.
vidu/image-to-video-2.0
$0.2
Bring your images to life by turning them into dynamic videos that capture your vision and action.
vidu/reference-to-video-2.0
$0.2
Create videos that align with reference subjects—like characters, objects, and environments—using the world’s first Multi-Entity Consistency feature.