curl --request POST \
--url https://api.modellix.ai/api/v1/vidu/viduq4-r2v \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"prompt": "The character waves hello.",
"reference_images": [
"https://example.com/subject.jpg"
]
}
'{
"code": 0,
"message": "success",
"data": {
"status": "pending",
"task_id": "task-vidu-q4-r2v-001",
"model_id": "vidu/viduq4-r2v",
"get_result": {
"method": "GET",
"url": "https://api.modellix.ai/api/v1/tasks/task-vidu-q4-r2v-001"
}
}
}{
"code": 400,
"message": "Invalid parameters: parameter 'first_frame_image' is required"
}{
"code": 401,
"message": "Authentication failed: invalid API key"
}{
"code": 429,
"message": "Rate limit exceeded: 100 requests per minute, retry after 60 seconds"
}{
"code": 500,
"message": "Internal server error"
}Vidu Q4 R2V
[Core Function] Vidu Q4 R2V is the preview reference-to-video model that composes a new 3-16 second clip from 1 to 15 reference images while keeping subject appearance consistent. [Strengths] It supports 540p through 4K, aspect ratios including 3:4 and 4:3, synchronized audio, and up to three reference audio clips. [Best For] Highly recommended for: multi-image character consistency, vertical 3:4 portraits, and scenes that combine reference images with spoken audio. [Limitations] Do NOT use this model to animate one image exactly as the first frame; use Vidu Q4 I2V for that. Do NOT omit the prompt. Do NOT send more than 15 images or more than 3 audio files. Subject-library invocation is not supported. [Routing] Use this model when the user supplies reference images and a prompt for a newly composed shot. Use Vidu Q4 I2V for a single start frame.
curl --request POST \
--url https://api.modellix.ai/api/v1/vidu/viduq4-r2v \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"prompt": "The character waves hello.",
"reference_images": [
"https://example.com/subject.jpg"
]
}
'{
"code": 0,
"message": "success",
"data": {
"status": "pending",
"task_id": "task-vidu-q4-r2v-001",
"model_id": "vidu/viduq4-r2v",
"get_result": {
"method": "GET",
"url": "https://api.modellix.ai/api/v1/tasks/task-vidu-q4-r2v-001"
}
}
}{
"code": 400,
"message": "Invalid parameters: parameter 'first_frame_image' is required"
}{
"code": 401,
"message": "Authentication failed: invalid API key"
}{
"code": 429,
"message": "Rate limit exceeded: 100 requests per minute, retry after 60 seconds"
}{
"code": 500,
"message": "Internal server error"
}Authorizations
API Key authentication. Format: Bearer YOUR_API_KEY.
Body
Vidu Q4 Preview reference-to-video request. Requires a prompt and 1-15 reference images.
Required scene description, up to 20000 characters. Reference tokens such as [@reference_image_1] are passed through unchanged.
1 - 20000"In the scene, the character waves hello."
Reference image URLs, 1 to 15. Appearance is preserved while the prompt defines the new action.
1 - 15 elements1["https://example.com/subject.jpg"]
Optional reference audio URLs, up to 3 mp3 files.
31["https://example.com/voice.mp3"]
Whether to generate audio with the video. Default true. Set false for a silent video.
true
Video duration in seconds. Default 5. Allowed range: 3-16.
3 <= x <= 165
Output aspect ratio. Default 16:9.
16:9, 9:16, 1:1, 3:4, 4:3 "3:4"
Video resolution. Default 720p. Allowed values: 540p, 720p, 1080p, 2K, 4K.
540p, 720p, 1080p, 2K, 4K "720p"
Random seed. Omit or use 0 for a random seed.
1