Context
4K
Input
image, text
Output
video
Tool calling
Not listed
About this model
Vidu-Q1-Img2Video is a 20B-parameter diffusion model specialized in transforming static images into dynamic, high-quality video sequences. Features advanced style preservation, motion transfer, and temporal coherence with exceptional input image fidelity and realistic motion synthesis.
Input modalities
image
Accepted as model input
text
Accepted as model input
Providers
Available routing options for this model through OneInfer.
Available
Video generation
$0.500 / video
Routing
OneInfer optimized
Pricing
Current OneInfer pricing for this model.
| Usage | Price |
|---|---|
| Video generation1920*1080 | $0.500 / video |
Performance
Published evaluation results associated with this model.
Animation Quality
Style Consistency96.3
Input Fidelity94.8
Temporal Flicker3.2
PSNR31.5
SSIM0.912
Motion Transfer
Motion Realism90.7
Physics Accuracy89.2
Object Permanence93.6
Depth Consistency95.1
Application Scores
Character Animation93.7
Landscape Cinemagraphs92.4
Product Visualization90.2
Historical Photo Animation88.9
Artwork Animation94.6
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": "Viduai/Vidu-Q1-Img2Video",
"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"
}'