image-to-video

PixVerse V5.5 - Create video from image

Generate a video from an image using the PixVerse-V5.5 model.

Compared to PixVerse-V5, version 5.5 adds:

  • 10-second duration (in addition to 5s and 8s; 10s capped at 720p)
  • Native audio generation via generate_audio_switch
  • Multi-clip output with dynamic camera changes via generate_multi_clip_switch
  • Prompt reasoning enhancement via thinking_type
post/v1/ai/image-to-video/pixverse-v5-5

Request

  • Base URL: https://api.magnific.com
  • URL: https://api.magnific.com/v1/ai/image-to-video/pixverse-v5-5
  • Auth: API key in header x-magnific-api-key

Request body

promptstring required

Prompt describing the video to generate

image_urlstring uri required

URL of the image to use as the first frame

resolution'360p' | '540p' | '720p' | '1080p'

The resolution of the generated video

aspect_ratio'widescreen_16_9' | 'classic_4_3' | 'square_1_1' | 'traditional_3_4' | 'social_story_9_16'

The aspect ratio of the generated video

duration5 | 8 | 10

The duration of the generated video in seconds. 8s videos cost double. 10s videos are only available up to 720p. 1080p videos are limited to 5 or 8 seconds.

negative_promptstring

Negative prompt to be used for the generation

style'anime' | '3d_animation' | 'clay' | 'cyberpunk' | 'comic'

The style of the generated video

seedinteger

The same seed and the same prompt given to the same version of the model will output the same video every time

camera_movement'horizontal_left' | 'horizontal_right' | 'vertical_up' | 'vertical_down' | 'zoom_in' | 'zoom_out' | 'crane_up' | 'quickly_zoom_in' | 'quickly_zoom_out' | 'smooth_zoom_in' | 'camera_rotation' | 'robo_arm' | 'super_dolly_out' | 'whip_pan' | 'hitchcock' | 'left_follow' | 'right_follow' | 'pan_left' | 'pan_right' | 'fix_bg'

The type of camera movement to apply to the video

generate_audio_switchboolean

When set to true, PixVerse-V5.5 generates synchronized audio (background music, sound effects, or dialogue) together with the video.

generate_multi_clip_switchboolean

When set to true, PixVerse-V5.5 produces multi-clip output with dynamic camera changes within a single generation.

thinking_type'enabled' | 'disabled' | 'auto'

Prompt reasoning enhancement mode. Controls how PixVerse-V5.5 optimizes the input prompt before generation.

  • enabled - The model rewrites the prompt automatically for better results.
  • disabled - The prompt is used exactly as written, with no rewriting.
  • auto - The model decides whether to rewrite the prompt based on the input.
webhook_urlstring uri

Optional callback URL that will receive asynchronous notifications whenever the task changes status. The payload sent to this URL is the same as the corresponding GET endpoint response, but without the data field.

Example request

{
  "style": "anime",
  "webhook_url": "https://www.example.com/webhook"
}

Response

OK

Example response

{
  "data": {
    "generated": [
      "https://openapi-generator.tech",
      "https://openapi-generator.tech"
    ],
    "task_id": "046b6c7f-0b8a-43b9-b35d-6489e6daee91",
    "status": "CREATED"
  }
}

Changes

No recorded changes to this operation across all 1 revision of this API.