Wan 2.7 Image-to-Video API

Overview

Wan 2.7 Image-to-Video is Alibaba's Wan-family image-to-video interface on iCreat: it turns one required starting image into a 4–15 second video, directed by a required text prompt. The starting image defines the opening composition, subject identity, environment, and visual style; the prompt directs motion, camera behavior, and scene development. Native audio is generated automatically with the video. The model is called through the async task queue at aliyun/wan2-7/image-to-video-sp, with 720P / 1080P output, five aspect ratios, and 4–15 second durations.

aliyun/wan2-7/image-to-video-sp

Core Capabilities

First-frame image-to-video generation. The uploaded image establishes the opening frame, main subject, scene layout, colors, and style. The model animates from that source instead of generating the entire composition from text alone.

Prompt-directed motion. A required prompt controls subject motion, camera movement, scene development, and visual treatment of the generated video.

Negative prompt control. Use negative_prompt to reduce unwanted objects, visual artifacts, abrupt cuts, style changes, or camera behavior. It improves control but does not guarantee complete removal.

Automatic native audio. Native audio (matching music and sound effects) is generated with the video automatically. No audio upload or separate audio-generation request is required.

Dual resolution. 720P for low-cost tests and repeated iteration; 1080P for final delivery that needs more visible detail.

Five aspect ratios. 1:1, 9:16, 16:9, 3:4, and 4:3 cover square feeds, vertical short video, and landscape formats.

4–15 second durations. Any integer duration from 4 to 15 seconds, sized for teasers, loops, and short social clips.

Watermark control. watermark defaults to false; enable it when an AI-generated mark is required.

Async task design. Submit → poll → retrieve keeps the workflow batch-friendly, fault-tolerant, and easy to integrate.

Model Comparison

Wan 2.7 Image-to-Video vs Seedance 2.5 Image-to-Video vs Kling V3 Omni

Input

A required text prompt and one required starting image (first frame). The negative prompt is optional.

The source image should clearly show the main subject, composition, lighting, and visual style. Conflicting details, heavy blur, extreme cropping, or unclear anatomy can make the generated motion less stable.

Input Examples

With negative prompt

{
  "input": {
    "prompt": "A running kitten",
    "negative_prompt": "The kitten should not run in a straight line",
    "media": [
      {
        "type": "first_frame",
        "url": "https://example.com/cat.jpg"
      }
    ]
  },
  "parameters": {
    "resolution": "720P",
    "ratio": "1:1",
    "duration": 5,
    "watermark": false
  }
}

Without negative prompt

{
  "input": {
    "prompt": "A kitten running across a grassy field",
    "media": [
      {
        "type": "first_frame",
        "url": "https://example.com/cat.jpg"
      }
    ]
  },
  "parameters": {
    "resolution": "1080P",
    "ratio": "16:9",
    "duration": 5,
    "watermark": false
  }
}

Parameters

input fields

parameters fields

Pricing

Total Cost = Unit Price × Output Video Duration

Native audio is generated automatically — there is no additional audio charge.

Quick Start

This API uses an API Key for authentication. Get your API Key from https://icreat.ai/hub/keys.

Submit a request:

curl --fail-with-body --connect-timeout 10 --max-time 60 \
  -X POST https://api.icreat.ai/v1/task/submit/aliyun/wan2-7/image-to-video-sp \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "input": {
      "prompt": "A running kitten",
      "negative_prompt": "The kitten should not run in a straight line",
      "media": [
        {
          "type": "first_frame",
          "url": "https://icreat.ai/xxx.jpg"
        }
      ]
    },
    "parameters": {
      "resolution": "720P",
      "ratio": "1:1",
      "duration": 5,
      "watermark": false
    }
  }'

The server will return:

{
  "task_id": "task-xxx"
}

Poll the task status:

curl --connect-timeout 10 --max-time 60 \
  -X POST "https://api.icreat.ai/v1/task/query-status" \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
  "task_id": "task-xxx"
}'

When the status is SUCCEEDED, retrieve the result:

curl --connect-timeout 10 --max-time 60 \
  -X POST "https://api.icreat.ai/v1/task/get-result" \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
  "task_id": "task-xxx"
}'

Output

submit → task_id → query-status (SUCCEEDED) → get-result

After submitting the request, poll query-status with the returned task_id until the status becomes SUCCEEDED, then call get-result with the same task_id to retrieve the generated video (with native audio).

Use Cases

Animating product and character stills. Use an existing photo, illustration, or render as the first frame and direct the motion with a prompt — ideal for turning static assets into dynamic showcases.

Social short clips. 4–15 second teasers, loops, and clips sized for feeds and stories, with the aspect ratio matched to each platform.

Low-cost iteration. At $0.50 for a 720P 5-second clip, test multiple motion directions cheaply before committing to premium renders.

Consistent visual identity. Because the opening composition, subject, and style come from the uploaded image, batches of clips generated from the same starting frame stay visually consistent.

Limitations

Duration is limited to 4–15 seconds; longer narratives must be split across multiple requests and stitched in post.

Only 720P and 1080P resolutions are available.

Exactly one first-frame image is required per request; other reference input types (video, audio, last frame) are not supported by this interface.

resolution, ratio, and duration are required fields and must be included in every request.

FAQ

How do I get an API Key?

Create one at https://icreat.ai/hub/keys and pass it via the Authorization: Bearer header.

What does the first-frame image control?

The opening composition, main subject, environment, colors, and visual style. The prompt then directs motion, camera behavior, and scene development.

What does negative_prompt do?

Describes content that should not appear — e.g. "The kitten should not run in a straight line" — without rewriting the main prompt. It improves control but does not guarantee complete removal.

Is audio generated?

Yes. Native audio is generated with the video automatically; no audio input or extra request is needed.

Is the watermark on by default?

No. watermark defaults to false; set it to true to add the AI-generated mark.

How is the cost calculated?

Total Cost = Unit Price × Output Video Duration. For example, a 10-second 1080P video costs 0.15 × 10 = $1.50.

720P or 1080P?

Use 720P for fast, low-cost iteration; use 1080P for final delivery that needs more visible detail.