curl --request POST \
--url https://api.modellix.ai/api/v1/xai/grok-imagine-video-r2v \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"prompt": "The character runs across a snowy field under the northern lights",
"reference_images": [
"https://example.com/character.png"
]
}
'{
"code": 0,
"message": "success",
"data": {
"status": "pending",
"task_id": "task-xai-r2v-001",
"model_id": "xai/grok-imagine-video-r2v",
"get_result": {
"method": "GET",
"url": "https://api.modellix.ai/api/v1/tasks/task-xai-r2v-001"
}
}
}{
"code": 400,
"message": "Invalid parameters: parameter '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"
}Grok Imagine Video R2V
xAI’s reference-to-video model for placing specific characters or products into a new scene while keeping them recognizable, with generated audio. It uses up to seven reference images in clips up to 10 seconds at 480p or 720p.
POST
/
xai
/
grok-imagine-video-r2v
curl --request POST \
--url https://api.modellix.ai/api/v1/xai/grok-imagine-video-r2v \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"prompt": "The character runs across a snowy field under the northern lights",
"reference_images": [
"https://example.com/character.png"
]
}
'{
"code": 0,
"message": "success",
"data": {
"status": "pending",
"task_id": "task-xai-r2v-001",
"model_id": "xai/grok-imagine-video-r2v",
"get_result": {
"method": "GET",
"url": "https://api.modellix.ai/api/v1/tasks/task-xai-r2v-001"
}
}
}{
"code": 400,
"message": "Invalid parameters: parameter '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"
}Body
application/json
xAI Grok Imagine reference-to-video request. Generates a video from a prompt while preserving the subjects from up to 7 reference images. Duration is capped at 10 seconds.