Video Generation Models
Seedance 2.5 Video Generation MCP
Generate a Seedance 2.5 video using a primary image, up to 30 reference images, or a reference video. Available via REST API or MCP.
Seedance 2.5 Video Generation AI Prompts & Use Cases
After connecting this MCP tool to your AI assistant, you can ask the questions below. Replace bracketed placeholders with your own inputs and use the supported values in Arguments.
New to Nexscope MCP? Follow the connection guide, then use the prompts below. The Integration and Parameters & Response tabs contain the connection steps, call example, and technical reference.
1. Generate A Product Video
Prompt: Turn my product image [IMAGE_URL] into a [DURATION]-second video with Seedance 2.5. Follow this brief: [VIDEO_BRIEF]. Keep the product consistent with the reference and return the finished video when it is ready.
2. Generate A Video From Multiple Images
Prompt: Create a [DURATION]-second product video with Seedance 2.5 using these reference images: [IMAGE_URLS]. Follow [VIDEO_BRIEF] and preserve the product details visible in the images. Use between 1 and 30 images and return the finished video for review.
3. Generate A Video Using A Reference Clip
Prompt: Use these reference videos [VIDEO_URLS] to create a [DURATION]-second video with Seedance 2.5. Follow the motion and scene described in [VIDEO_BRIEF]. Use up to 5 reference clips without adding image references, and return the completed video.
4. Generate A Video In The Right Aspect Ratio
Prompt: Create a [DURATION]-second video from my product image [IMAGE_URL] for [PLACEMENT]. Follow [VIDEO_BRIEF] and use [ASPECT_RATIO]: 16:9 or 4:3 for landscape, 1:1 for square, 3:4 or 9:16 for portrait, or 21:9 for a wide layout. Return it for review without publishing it.
5. Generate A Video At A Chosen Resolution
Prompt: Create a [DURATION]-second video from [IMAGE_URL] following [VIDEO_BRIEF]. Use [RESOLUTION], choosing 480p, 720p or 1080p to match my delivery requirements. Send me the completed video for review.
6. Generate A 30-Second Product Video
Prompt: Create a 30-second product walkthrough from these reference images: [IMAGE_URLS]. Use between 1 and 30 images and follow this brief: [VIDEO_BRIEF]. Show the product details clearly and return the finished video for review.
7. Generate A Video From An Approved Brief
Prompt: Create a [DURATION]-second video from my product image [IMAGE_URL] using this approved brief: [VIDEO_BRIEF]. Keep prompt optimization and professional mode off. Return the completed video so I can check it against the brief.
8. Improve A Brief And Generate A Video
Prompt: Use Nexscope’s prompt optimization to improve this video brief: [VIDEO_BRIEF]. Create a [DURATION]-second video using my product image [IMAGE_URL], keeping the brief grounded in the supplied product facts. Return the finished video for review.
9. Generate A Video In Professional Mode
Prompt: Create a [DURATION]-second video from [IMAGE_URL] following [VIDEO_BRIEF], using professional mode if it is supported. If the mode is unavailable, tell me rather than changing the setting or starting another generation.
10. Generate A Vertical Product Video
Prompt: Create a [DURATION]-second vertical product video from these reference images: [IMAGE_URLS]. Use a 9:16 layout and 720p resolution, keep prompt optimization off, and follow [VIDEO_BRIEF]. Use between 1 and 30 images and return the finished video for review without publishing it.
What You Need to Provide
Provide a public reference image, a set of reference images, or reference videos, plus a brief of up to 2,000 characters. Choose a duration from 4 to 30 whole seconds.
Images must be JPEG, PNG or WebP, no larger than 20 MiB each, with width and height between 300 and 6,000 pixels. Reference videos must be MP4 or QuickTime and no larger than 20 MiB each.
Choose image references or video references for each request. Generation can take time: check the existing task with bounded retries, report if it is still processing, and do not submit it again. The Integration tab explains the task workflow.
Step 1 · Connect
Connect Your AI Assistant
Connect a compatible MCP client to Nexscope, then select this tool from your assistant. Use the connection settings in your client to complete authentication.
POST https://api.nexscope.ai/mcp
MCP-Protocol-Version: 2025-11-25
Content-Type: application/jsonAuthentication
Use OAuth 2.1 Authorization Code with PKCE and the mcp:tools scope. API keys remain supported as a compatibility option.
Authorization: Bearer nk-xxxxxxxxxxxxxxxxxUsing an API key? Get your key from API Access and include it in the Authorization header shown above.
Call this MCP tool
nexscope_seedance_2_5_video_generationhttps://api.nexscope.ai/mcptools/callInitialize an MCP 2025-11-25 Streamable HTTP session at https://api.nexscope.ai/mcp, then use tools/call.
{
"jsonrpc": "2.0",
"id": "seedance-2-5-video-generation-1",
"method": "tools/call",
"params": {
"name": "nexscope_seedance_2_5_video_generation",
"arguments": {
"imageUrl": "https://example.com/source-image.jpg",
"prompt": "Keep the product consistent while the camera slowly orbits and highlights material details.",
"resolution": "480p",
"videoTime": 5
}
}
}MCP 2025-11-25 · Streamable HTTPProgress is delivered on the original POST SSE response. GET SSE carries notifications; reconnecting must query existing asynchronous work rather than submit again.
Asynchronous task workflow
- 1. Create once
Keep the returned taskId.
- 2. Query with backoff
Use nexscope_media_task_result after 5 seconds, then 10, 20, and 30 seconds.
- 3. Use final result
Stop at success, failure, or timeout.
{
"jsonrpc": "2.0",
"id": "seedance-2-5-video-generation-result-1",
"method": "tools/call",
"params": {
"name": "nexscope_media_task_result",
"arguments": {
"skillSlug": "seedance-2-5-video-generation",
"taskId": "TASK_ID_FROM_THE_GENERATION_RESULT"
}
}
}Arguments
| Name | Type | Required | Description |
|---|---|---|---|
videoTime | integer | required | Video duration in seconds. Available options
Example: 5 |
prompt | string | required | Video generation prompt describing motion, subject consistency, camera movement, and the ecommerce scene. Maximum 2000 characters. Example: Keep the product consistent while the camera slowly orbits and highlights material details. |
promptOptimizer | boolean | optional | Whether Nexscope should optimize the video prompt before generation. Defaults to false. Example: false |
isPro | boolean | optional | Whether to use the model's professional generation mode when supported. Defaults to false. Example: false |
resolution | string | optional | Output resolution. Available options
Example: 480p |
imageUrl | string | optional | Public URL of a first-frame or primary reference image. Each image must be between 300 and 6000 pixels in both width and height. Example: https://example.com/source-image.jpg |
imageList | array | optional | Public reference image URLs. Provide 1 to 30 images. Each image must be between 300 and 6000 pixels in both width and height. Example: [
"https://example.com/product.jpg",
"https://example.com/ref-2.jpg"
] |
video | array | optional | Optional public reference-video URL list. Reference-video mode cannot be combined with image references or a final-frame image. Example: [
"https://example.com/reference-video.mp4"
] |
aspectRatio | string | optional | Target video aspect ratio supported by this model. Available options
Example: 16:9 |
Response fields
Treat structuredContent as the programmatic API response payload.
| Name | Type | Required | Description |
|---|---|---|---|
code | integer | required | 0 means accepted or successful; nonzero is a platform error. |
cost | string | required | Elapsed milliseconds, never credits; -1 outside web requests. |
data | any | required | Data value used by this API operation. |
msg | string | null | required | Msg value used by this API operation. |
time | string | required | Server local time: yyyy-MM-dd HH:mm:ss. |
traceId | string | null | required | Trace id value used by this API operation. |
ts | string | required | Epoch milliseconds. |
Any of option 1 — requires taskId, status, result
| Name | Type | Required | Description |
|---|---|---|---|
data | object | required | Data value used by this API operation. |
data.result | any | required | Completed generation output retained from the task result. Fields vary by capability; generated resources use Nexscope-hosted URLs and any count represents charged Nexscope credits. This is the business output, not a task creation receipt. |
data.status | string | required | Status value used by this API operation. Allowed: PENDING, RUNNING, SUCCEEDED, FAILED, TIMEOUT |
data.taskId | string | required | Task id value used by this API operation. |
Any of option 1
| Name | Type | Required | Description |
|---|---|---|---|
data.result | object | required | Completed generation output retained from the task result. Fields vary by capability; generated resources use Nexscope-hosted URLs and any count represents charged Nexscope credits. This is the business output, not a task creation receipt. |
Any of option 2
| Name | Type | Required | Description |
|---|---|---|---|
data.result | null | required | Completed generation output retained from the task result. Fields vary by capability; generated resources use Nexscope-hosted URLs and any count represents charged Nexscope credits. This is the business output, not a task creation receipt. |
Any of option 2
| Name | Type | Required | Description |
|---|---|---|---|
data | null | required | Data value used by this API operation. |
Format Illustration
Illustrative example with fictional data, not a live tool call.
Illustrative Question
Turn my product image into a five-second video with a slow camera orbit at 480p.
Illustrative Response Explanation
The illustrative response accepts the video task and returns a PENDING status. The video is not ready yet; keep the task ID and check for the completed result rather than submitting the same generation request again.
About this sample: Illustrative task-status example only. The image URL and task ID are placeholders, not a generated video or a live task. Replace the image with a supported accessible asset before submitting a real request.
Published sample data is not available for this page. A format illustration or workflow guide is not a substitute for a published result.
View the MCP Request & Response Format
Examples
Illustrative example with fictional data, not a live tool call.
The JSON-RPC envelope below illustrates how the shown arguments and payload fit into MCP. It is not captured network traffic or proof of a successful call. Workflow-only examples do not include a result.
MCP Request
{
"jsonrpc": "2.0",
"id": "seedance-2-5-video-generation-example",
"method": "tools/call",
"params": {
"name": "nexscope_seedance_2_5_video_generation",
"arguments": {
"imageUrl": "https://example.com/source-image.jpg",
"prompt": "Keep the product consistent while the camera slowly orbits and highlights material details.",
"resolution": "480p",
"videoTime": 5
}
}
}MCP Response Format
{
"jsonrpc": "2.0",
"id": "seedance-2-5-video-generation-example",
"result": {
"content": [
{
"type": "text",
"text": "{\"code\":0,\"msg\":null,\"data\":{\"result\":null,\"status\":\"PENDING\",\"taskId\":\"example-task\"},\"cost\":\"0\",\"time\":\"2026-01-01 00:00:00\",\"traceId\":null,\"ts\":\"1767225600000\"}"
}
],
"structuredContent": {
"code": 0,
"msg": null,
"data": {
"result": null,
"status": "PENDING",
"taskId": "example-task"
},
"cost": "0",
"time": "2026-01-01 00:00:00",
"traceId": null,
"ts": "1767225600000"
},
"isError": false
}
}