Video Generationimagetext

Vidu Q2 Reference

Shengshu Technology multi-reference image-to-video model

Input

Generation mode

This template only supports the following input

First-frame I2V

Describe the video with text only, no images required.

Prompt

Reference image (optional)

PNG, JPG or WebP · you can also drag and drop a file here

Duration

110

Resolution

Aspect ratio

Generate audio

Movement amplitude

Ready to generate

API Reference

POSThttps://api.token360.ai/v1/videos

# Step 1: Create video generation task
curl https://api.token360.ai/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
  "model": "viduq2-img2video",
  "prompt": "A cat walking across a room",
  "duration": 5,
  "resolution": "720p",
  "aspect_ratio": "16:9",
  "generate_audio": false,
  "movement_amplitude": "auto"
}'

# Step 2: Poll for completion (replace VIDEO_ID with the id from step 1)
curl https://api.token360.ai/v1/videos/VIDEO_ID \
  -H "Authorization: Bearer your-api-key"