Novita

wan2.2-t2v

Qwen/Wan2.2-T2V
Context

2K

Input

text

Output

video

Tool calling

Not listed

About this model

Wan2.2-T2V-A14B is a 14B-parameter text-to-video diffusion model specializing in high-fidelity motion generation and temporal consistency. Features advanced motion dynamics modeling and cinematic quality rendering with 128-frame coherence support.

Input modalities

text

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Available

Video generation

$0.300 / video

Video generation

$0.400 / video

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Video generation832*480$0.300 / video
Video generation480*832$0.300 / video
Video generation624*624$0.300 / video
Video generation1920*1080$0.400 / video
Video generation1080*1920$0.400 / video
Video generation1440*1440$0.350 / video
Video generation1248*1632$0.350 / video

Performance

Published evaluation results associated with this model.

Video Quality

FVD-25618.7
CLIP-TempScore32.4
PSNR28.9

Motion Fidelity

Motion Consistency91.2
Object Permanence89.7
Temporal Stability93.5

Style Range

Cinematic88.4
Anime85.2
Documentary83.7
3D Animation81.9

API example

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": "Qwen/Wan2.2-T2V",
  "prompt": "A red fox running through a snowy forest",
  "resolution": "832*480",
  "aspect_ratio": "16:9",
  "duration": 5,
  "generate_audio": false,
  "camera_fixed": false,
  "service_tier": "default"
}'