Pika V2 5 Image To Video
5s minimum, from 180 credits
ae_pika_v2_5_image_to_video
Turn a still image into a 5- or 10-second video using a text prompt, with resolution and refinement options.
5s minimum, from 180 credits
Pricing
| Resolution | Video duration (seconds): 5 / Not specified | Video duration (seconds): 10 |
|---|---|---|
| 480p | 180 credits/call | 360 credits/call |
| 720p / Not specified | 300 credits/call | 600 credits/call |
| 1080p | 600 credits/call | 1200 credits/call |
Starting price applies to Video duration (seconds): 5, Resolution: 480p.
Parameters
Optional parameters use the platform defaults when omitted.
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
request_body | object | Yes | No parameter description. | — |
request_body.seed | integer | unknown | No | The seed for the random number generator | — |
request_body.prompt | string | Yes | No parameter description. | — |
request_body.duration | enum (5 | 10) | No | The duration of the generated video in seconds | 5 |
request_body.image_url | string | Yes | URL of the image to use as the first frame | — |
request_body.resolution | enum (480p | 720p | 1080p) | No | The resolution of the generated video | 720p |
request_body.negative_prompt | string | No | A negative prompt to guide the model | ugly, bad, terrible |
Invocation example
Copy the request and explore its response example.
POST
/agent-api/v1/tool/executeX-Api-KeySubmit first, then query with the returned task_id until the task completes.
Request coderequest.sh
curl --request POST \
--url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_pika_v2_5_image_to_video' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {
"request_body": {
"duration": 5,
"image_url": "https://d2h7xmz5gqybh9.cloudfront.net/output/f118e14b-080a-4305-8908-939322814be1.png",
"negative_prompt": "camera movement, zoom, people turning around, faces visible, third person, color, cartoon",
"prompt": "Static surveillance camera view, absolutely no camera movement. Two figures keep sitting with their backs to the camera at the stone table. The smaller figure slides a bamboo scroll toward the older figure'\''s hand. The older figure raises his right hand and taps twice in front of the glowing laptop screen, then lowers his hand. The smaller figure leans forward slightly toward the screen. Both stay seated, never turn around. Black and white, heavy grain, dim.",
"resolution": "480p"
}
}
}'Response exampleresponse.json
{
"description": "task accepted; poll the result via query_tool with this task_id",
"query_tool": "ae_get_result",
"status": "created",
"task_id": "c4cc5e43-2902-4496-bc64-c93d35fffb2c"
}





