Wan 2.7 Image-to-Video Spicy

Wan 2.7 Image-to-Video SP API

Overview

Wan 2.7 Image-to-Video SP turns one required starting image into a 4–15 second video with automatic native audio at 720P or 1080P. SP means spicy: an uncensored version designed for mature NSFW creation without standard content filters.

Access is limited to adults aged 18 and over and remains subject to applicable laws and prohibited-content rules. Spicy access does not mean illegal content is permitted.

The starting image defines the opening composition, subject identity, environment, and visual style. A required Prompt directs motion, camera behavior, scene development, and visual treatment. An optional Negative Prompt helps reduce unwanted content, artifacts, cuts, or camera behavior.

Use the model through:

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

Key Features

Spicy Image-to-Video access. Wan 2.7 SP removes standard content filters for lawful mature 18+ generation while keeping the workflow focused on one required starting image.

Required first-frame control. 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.

Negative Prompt control. Use negative_prompt to reduce unwanted objects, visual artifacts, abrupt cuts, style changes, anatomy errors, or camera behavior. It can improve control but does not guarantee complete removal.

Automatic native audio. Native audio is generated with the video automatically. No audio upload or separate audio-generation request is required.

720P and 1080P output. Use 720P for lower-cost tests and repeated iteration. Use 1080P for selected results that need more visible detail.

Flexible duration and framing. Choose any integer duration from 4 to 15 seconds and use 1:1, 9:16, 16:9, 3:4, or 4:3 for square, vertical, landscape, and portrait output.

Model Comparison

Wan 2.7 SP vs Wan 2.7

Wan 2.7 SP vs Wan 2.6 Spicy vs Seedance 1.5 Pro Spicy vs Wan 2.2 Spicy

Inputs

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.

Parameters

Pricing

Total Cost = Unit Price × Output Video Duration

Native audio is generated automatically.

Quick Start

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": "The subject slowly turns toward the camera while soft fabric and hair move naturally. Add a gentle camera push-in and keep the original lighting and visual style.",
      "negative_prompt": "distorted anatomy, extra limbs, unstable face, sudden cut, flickering, abrupt camera movement, text, logo",
      "media": [
        {
          "type": "first_frame",
          "url": "https://example.com/source-image.jpg"
        }
      ]
    },
    "parameters": {
      "resolution": "1080P",
      "ratio": "16:9",
      "duration": 8,
      "watermark": false
    }
  }'

The request returns a task_id.

Submit request → Receive task_id → Poll status → Retrieve result

Query the task status until it reaches SUCCEEDED, then use the same task_id to retrieve the result.

Output

Wan 2.7 Image-to-Video SP uses an asynchronous task flow.

The submission request returns a task_id. Task status is checked through the query-status endpoint, and the completed result is retrieved through the get-result endpoint after the task succeeds.

Detailed result fields are not listed until they are confirmed from an actual iCreat response.

Use Cases

Mature portrait animation. Animate expressions, breathing, hair, clothing, and subtle camera movement from one lawful adult source portrait.

Adult fictional scene development. Turn lawful mature artwork or character images into short scene concepts with motion and native audio.

Cinematic artwork animation. Add atmosphere, lighting changes, environmental motion, and camera behavior to a still image.

Age-restricted promotional concepts. Create short concepts for lawful adult products, services, or entertainment.

Audio-video scene generation. Generate visual motion and native sound together without uploading a soundtrack or calling a separate audio model.

Limitations

Wan 2.7 Image-to-Video SP is available only to adults aged 18 and over. Requests remain subject to applicable laws and prohibited-content rules. Removing standard content filters does not permit illegal content.

The workflow requires one starting image and does not accept a last frame, video input, or audio input. Output length is limited to 4–15 seconds.

The source image may not be preserved exactly. Identity, anatomy, small details, text, fast motion, continuity, and audio timing can vary. Negative Prompts can reduce unwanted results but cannot guarantee complete removal.

A selected output ratio that differs from the source image may cause cropping, reframing, or added space around the subject.

FAQ

What does SP mean in Wan 2.7?

SP means spicy. It is the uncensored version of Wan 2.7 Image-to-Video, designed for mature NSFW generation without standard content filters. Access is limited to adults aged 18 and over and remains subject to applicable laws and prohibited-content rules.

Is Wan 2.7 SP completely unrestricted?

No. SP removes standard content filtering, but illegal content and other prohibited uses are not allowed. It should not be described as unlimited, rule-free, or open to every request.

What type of starting image works best?

Use a clear image with a visible main subject, stable anatomy, deliberate composition, and enough space for the intended motion. Heavy blur, extreme crops, unclear limbs, or conflicting visual details can reduce stability.

Does Wan 2.7 SP preserve the source image exactly?

No. The source image guides the opening composition, identity, environment, and style, but generated motion can change small details, textures, facial features, clothing, or background elements.

Does it generate audio automatically?

Yes. Native audio is generated with the video automatically. No audio input or separate audio request is required.

How should a Negative Prompt be written for Image-to-Video?

List the specific errors, cuts, objects, or camera behavior you want to avoid. Short phrases such as unstable face, extra limbs, flickering, sudden cut, or abrupt camera movement are clearer than long contradictory instructions.

When should 1080P be used instead of 720P?

Use 720P for lower-cost testing and repeated prompt iteration. Use 1080P for selected outputs that need more visible detail or a larger delivery size.

Can it use a last frame, video, or audio file?

No. This endpoint uses one required starting image. It does not expose last-frame, video-input, or audio-input controls.

Why does the output crop or reframe the source image?

The selected output ratio may differ from the source image ratio. The model may crop, extend, or reposition parts of the image to fit the requested frame shape and generated movement.