PixVerse V6 Image To Video
From 30 credits/sec
ae_pixverse_v6_image_to_video
Animate an image into a prompt-guided video with style, negative prompt, duration, resolution, optional audio, and multi-clip camera changes.
From 30 credits/sec
Pricing
From 30 credits/sec
| Resolution | Generate audio: Disabled / Not specified | Generate audio: Enabled |
|---|---|---|
| 360p | 30 credits/second | 42 credits/second |
| 540p | 42 credits/second | 54 credits/second |
| 720p / Not specified | 54 credits/second | 72 credits/second |
| 1080p | 108 credits/second | 138 credits/second |
When duration is omitted, billing is based on five seconds. Starting price applies to Generate audio: Disabled, Resolution: 360p.
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 same seed and the same prompt given to the same version of the model will output the same video every time. | — |
request_body.style | string | unknown | No | The style of the generated video | — |
request_body.prompt | string | Yes | No parameter description. | — |
request_body.duration | integer | No | The duration of the generated video in seconds. v6 supports values from 1 to 15 seconds | 5 |
request_body.image_url | string | Yes | URL of the image to use as the first frame | — |
request_body.resolution | enum (360p | 540p | 720p | 1080p) | No | The resolution of the generated video | 720p |
request_body.thinking_type | string | unknown | No | Prompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision | — |
request_body.negative_prompt | string | No | Negative prompt to be used for the generation | "" |
request_body.generate_audio_switch | boolean | No | Enable audio generation (BGM, SFX, dialogue) | false |
request_body.generate_multi_clip_switch | boolean | No | Enable multi-clip generation with dynamic camera changes | false |
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_pixverse_v6_image_to_video' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {
"request_body": {
"duration": 3,
"generate_audio_switch": false,
"image_url": "https://v3b.fal.media/files/b/0ab21f8b/FF2WjxFrLWvG6o5_xqgco_5rKV9eX9.png",
"negative_prompt": "text appearing, handwriting, letters, chinese characters, printed words, hands, fingers, people, face, pen, camera shake, fast zoom, pan, tilt, subtitle, caption, watermark, cool white daylight, overexposed, cartoon, anime, distortion, blurry, low quality",
"prompt": "Locked-off static macro camera with an extremely slow gentle push-in. An old folded paper held up against a warm desk lamp at deep night, paper fibers glow through the amber backlight, the frayed crease edges tremble very slightly, absolutely no writing and no ink appearing on the paper, deep dark old room around, realistic cinematic texture, 35mm film grain, high dynamic range, deep shadows. No subtitles, no text, no music.",
"resolution": "360p",
"seed": 2026111244
}
}
}'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": "318a52fd-7821-4df2-ac46-652494ad6b1b"
}Guides using this tool
See how this tool fits into real workflows
Image-to-Video Generation with AI AgentsUse natural language to turn a static image or product shot into a short video with camera motion: one image becomes dynamic footage, with controllable length and shots, plus multi-model comparison and batch output.AI Video Generation Workflow with AI AgentsRun text-to-video, image-to-video, and reference-keyframe video generation through one AI agent: pick the path by your starting material, compare models, and choose the best cut — no separate sign-ups.




