Grok Imagine Video R2V

[Core Function] Grok Imagine Video R2V generates a video from a text prompt while preserving the subjects shown in up to 7 reference images. [Strengths] It excels at keeping character/subject identity consistent across a newly generated scene driven by the prompt. [Best For] Highly recommended for: character-driven video, placing a specific subject into a new scene, and blending features from multiple references. [Limitations] Do NOT use this model to simply animate a single image as-is (use Image-to-Video), or for clips longer than 10 seconds or resolutions above 720p; duration is capped at 10s and resolution at 480p/720p. [Routing] Use this model when the user provides reference images of a subject and wants a new action/scene described by a prompt. To simply animate a single image as-is, use Image-to-Video.

POST /xai/grok-imagine-video-r2v

cURL

basic

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"
  ]
}
'

200

{
  "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"
    }
  }
}

Authorizations

Authorization · string · header · required

API Key authentication. Format: Bearer YOUR_API_KEY.

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.

prompt · string · required

Text description of the video to generate

Minimum string length: 1

Example:

"The character runs across a snowy field under the northern lights"

reference_images · string[] · required

Reference images (1-7) whose subjects are preserved in the generated video. Each item is a publicly accessible image URL or a base64 data URI.

Required array length: 1 - 7 elements

Minimum string length: 1

Example:

["https://example.com/character.png"]

duration · integer · default: 8

Video duration in seconds (max 10 when using reference images)

Required range: 1 <= x <= 10

Example:

10

aspect_ratio · enum<string>

Video aspect ratio

Available options: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3

Example:

"16:9"

resolution · enum<string> · default: 480p

Video resolution

Available options: 480p, 720p

Example:

"720p"

Response

200

application/json

Task submitted successfully

code · integer · required

Response code, 0 indicates success

Example:

0

message · string · required

Response message

Example:

"success"

data · object · required

Detailed data about the submitted asynchronous task.

Show child attributes