Image-to-Video API Reference - Magic Hour Docs

What this API does

Create the same Image To Video you can make in the browser, but programmatically, so you can automate it, run it at scale, or connect it to your own app or workflow.

Good for

• Automation and batch processing
• Adding image to video into apps, pipelines, or tools

How it works (3 steps)

1. Upload your inputs (video, image, or audio) with Generate Upload URLs and copy the file_path.
2. Send a request to create a image to video job with the basic fields.
3. Check the job status until it’s complete, then download the result from downloads.

Key options

• Inputs: usually a file, sometimes a YouTube link, depending on project type
• Resolution: free users are limited to 576px; higher plans unlock HD and larger sizes
• Extra fields: e.g. face_swap_mode, start_seconds/end_seconds, or a text prompt

Cost
Credits are only charged for the frames that actually render. You’ll see an estimate when the job is queued, and the final total after it’s done.

For detailed examples, see the product page.

POST /v1/image-to-video

Python

Python

from magic_hour import Client
from os import getenv

client = Client(token=getenv("API_TOKEN"))
res = client.v1.image_to_video.generate(
    assets={"image_file_path": "/path/to/1234.png"},
    end_seconds=5.0,
    name="Image To Video video",
    resolution="720p",
    wait_for_completion=True,
    download_outputs=True,
    download_directory="."
)

200

{
  "id": "cuid-example",
  "credits_charged": 450
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <api_key>, where <api_key> is your API key. To get your API key, go to Developer Hub and click "Create new API Key".

Body

application/json

Body

end_seconds · number<float> · required

The total duration of the output video in seconds. Supported durations depend on the chosen model:

• ltx-2.3: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 15, 20, 25, 30
• wan-2.2: 3, 4, 5, 6, 7, 8, 9, 10, 15
• kling-2.5: 5, 10
• kling-3.0: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
• veo3.1-lite: 8, 16, 24, 32, 40, 48, 56
• veo3.1: 4, 6, 8, 16, 24, 32, 40, 48, 56
• seedance: 4, 5, 6, 7, 8, 9, 10, 11, 12
• seedance-2.0: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
• sora-2: 4, 8, 12, 24, 36, 48, 60

Required range: 1 <= x <= 60

Example:

5

assets · object · required

Provide the assets for image-to-video. Sora 2 only supports images with an aspect ratio of 9:16 or 16:9.

Show child attributes

name · string · default: Image To Video - dateTime

Give your video a custom name for easy identification.

Example:

"My Image To Video video"

model · enum<string> · default: default

The AI model to use for video generation.

• default: uses our currently recommended model for general use. For paid tiers, defaults to kling-3.0. For free tiers, it defaults to ltx-2.3.
• ltx-2.3: Fast iteration with lip-sync & end frame
• wan-2.2: Fast, strong visuals with effects
• kling-2.5: Motion, action, and camera control
• kling-3.0: Cinematic, multi-scene storytelling
• veo3.1-lite: Fast, affordable, high-quality
• veo3.1: Realistic visuals and prompt adherence
• seedance: Fast iteration and start/end frames
• seedance-2.0: State-of-the-art quality and consistency
• sora-2: Story-first concepts and creativity

If you specify the deprecated model value that includes the -audio suffix, this will be the same as included audio as true.

Available options: default, ltx-2, ltx-2.3, wan-2.2, seedance, seedance-2.0, kling-2.5, kling-3.0, veo3.1, veo3.1-lite, sora-2, kling-1.6, kling-2.5-audio, veo3.1-audio

Example:

"kling-3.0"

resolution · enum<string>

Controls the output video resolution. Defaults to 720p on paid tiers and 480p on free tiers.

• ltx-2.3: Supports 480p, 720p, 1080p.
• wan-2.2: Supports 480p, 720p, 1080p.
• kling-2.5: Supports 720p, 1080p.
• kling-3.0: Supports 720p, 1080p, 4k.
• veo3.1-lite: Supports 720p, 1080p.
• veo3.1: Supports 720p, 1080p.
• seedance: Supports 480p, 720p, 1080p.
• seedance-2.0: Supports 480p, 720p.
• sora-2: Supports 720p.

Available options: 480p, 720p, 1080p, 4k

Example:

"720p"

audio · boolean

Whether to include audio in the video. Defaults to false if not specified.

Audio support varies by model:

• ltx-2.3: Toggle-able: no additional credits for audio
• wan-2.2: Not supported
• kling-2.5: Toggle-able: no additional credits for audio
• kling-3.0: Toggle-able: audio adds extra credits when enabled
• veo3.1-lite: Toggle-able: audio adds extra credits when enabled
• veo3.1: Toggle-able: audio adds extra credits when enabled
• seedance: Not supported
• seedance-2.0: Toggle-able: no additional credits for audio
• sora-2: Toggle-able: no additional credits for audio

Example:

true

style · object

Attributed used to dictate the style of the output

Show child attributes

Response

200

application/json

Success

Success

id · string · required

Unique ID of the video. Use it with the Get video Project API to fetch status and downloads.

Example:

"cuid-example"

credits_charged · integer · required

The amount of credits deducted from your account to generate the video. If the status is not 'complete', this value is an estimate and may be adjusted upon completion based on the actual FPS of the output video.

If video generation fails, credits will be refunded, and this field will be updated to include the refund.

Example:

450