Wan 2.6 Spicy Image-to-Video API by Atlas Cloud

Wan 2.6 Spicy Image-to-Video

Wan 2.6 Spicy Image-to-Video turns a first-frame image into a short motion clip with expressive character movement and stable temporal detail. This AtlasCloud variant uses a dedicated Wan 2.6 image-to-video LoRA deployment for a more stylized motion profile.

Highlights

• First-frame image-to-video: Use one starting image plus a text prompt to control movement and camera direction.
• 720p, 1080p, and SR output: Use native 720p/1080p, or choose 1080p-SR / 1440p-SR for FlashVSR super-resolution from a 720p source.
• Short-form generation: Supports 5s, 10s, and 15s clips.
• Optional audio control: Provide an audio URL to guide motion, or disable generated audio for silent output.
• Negative prompt support: Add optional constraints to reduce blur, distortion, or unwanted artifacts.

Parameters

How To Use

curl -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \
  -H "Authorization: Bearer $AIP_API_KEY" \
  -H "Content-Type: application/json" \
  --data-raw '{
    "model": "atlascloud/wan-2.6-spicy/image-to-video",
    "prompt": "The woman turns toward the camera with a confident smile, hair moving naturally as the camera slowly pushes in.",
    "image": "https://static.atlascloud.ai/media/images/db548fe3bd5cafa4ef7e0141d69c8566.jpeg",
    "negative_prompt": "blurry, low quality, distorted hands, extra limbs",
    "duration": 5,
    "resolution": "720p",
    "generate_audio": true,
    "seed": -1
  }'

Pricing

Pricing uses Wan 2.6 Image-to-Video native-resolution multipliers before account or environment discounts. SR tiers are priced at 80% of the equivalent native-resolution price.

Formula:

sku_base * max(5, duration) * (
  resolution == "1440p-sr" ? 2.1333 :
  (resolution == "1080p-sr" ? 1.2 :
    (resolution == "1080p" || resolution == "1080P" ? 1.5 : 1))
)

sku_base = $0.1000/s for 720p. The runtime then applies the model/account discount configured in that environment.

Notes

• This model is allowlist-enabled. Contact AtlasCloud if it is not visible or callable from your account.
• 480p is not exposed for this model.
• This endpoint uses the input image as the first frame of the generated video.
• shot_type: "multi" requires enable_prompt_expansion: true.
• Native 720p and 1080p call the underlying deployment directly. SR modes first generate a 720p source, then upscale with FlashVSR.
• Generation is asynchronous. Poll /api/v1/model/prediction/{request_id} for the final video URL.