vidu-q1-text2video

Viduai/Vidu-Q1-Text2Video

Context

Input

text

Output

video

Tool calling

Not listed

About this model

Vidu-Q1-Text2Video is an 18B-parameter diffusion model specializing in high-quality text-to-video generation with exceptional motion dynamics and temporal coherence. Features advanced physics-aware motion modeling and cinematic-quality rendering with extended context understanding.

Compare Video Models

Input modalities

text

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Novita

Available

Video generation

$0.500 / video

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

Usage	Price
Video generation1920*1080	$0.500 / video
Video generation1080*1920	$0.500 / video
Video generation1440*1440	$0.500 / video

Performance

Published evaluation results associated with this model.

Video Quality

FVD-25616.8

CLIP-TempScore34.2

PSNR30.1

SSIM0.893

Motion Fidelity

Physics Accuracy88.9

Motion Consistency93.7

Temporal Stability94.2

Object Permanence91.5

Content Understanding

Complex Prompt Handling89.3

Style Adaptation87.6

Multi-Object Scenes85.4

Long-Context Coherence91.8

API example

Refer Documentation

curl -X POST https://api.oneinfer.ai/v1/ula/generate-video \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "provider": "novita",
  "model": "Viduai/Vidu-Q1-Text2Video",
  "prompt": "A red fox running through a snowy forest",
  "resolution": "1920*1080",
  "aspect_ratio": "16:9",
  "duration": 5,
  "generate_audio": false,
  "camera_fixed": false,
  "service_tier": "default"
}'