Skip to main content

Image to Video Ultra Endpoint

Overview​

Image to Video Ultra endpoint helps generate HD video, with high quality and high resolution, from a given init_image.

Experience the next level of AI-driven video creation with Image-to-Video Ultra today! 🚀

Each API call costs $0.2, which is equivalent to 31 credits from the Basic Plan (3250 API Credits) and 43 credits from the Standard Plan (10000 API Credits).

With the Unlimited Plan for the Image-to-Video Ultra endpoint, you can generate unlimited videos.​

Open in Playground 🚀

Example Video Generation​

Request​

--request POST 'https://modelslab.com/api/v6/video/img2video_ultra' \

Make a POST request to https://modelslab.com/api/v6/video/img2video_ultra endpoint and pass the required parameters in the request body.

Body Attributes​

ParameterDescriptionValues
keyYour API Key used for request authorization.key
promptText prompt with a description of the things you want in the video to be generated.String
model_idThe model ID to use for the video generation.wan2.2 or wan2.1 (Default: wan2.1)
init_imageLink equivalent of a valid PNG, JPEG, or other valid image format file to use as initial image conditioning.URL
negative_promptItems you don't want in the video.String
seedSeed is used to reproduce results. The same seed will give you the same image again. Pass null for a random number.Integer or null
resolutionthe resolution of the generated outputThe maximum is 480 .
num_framesThe number of frames in the generated video. Default is 81Integer
num_inference_stepsNumber of denoising steps. Default is 20. Maximum is 25.Integer (Default: 20, Max: 25).
guidance_scaleScale for classifier-free guidance. Minimum is 0.0, maximum is 8.0min: 0.0, max: 8.0
fpsFrames per second rate of the generated video. Should be less than num_framesInteger (Default: 16, Max: 25)
portraitIndicates whether the output should be in portrait mode. It accepts true or false. Default falseBoolean
sample_shiftControls the sampling shift in the generation process. Default value is 5Integer (Default: 5, Max: 10)
output_typeThe format of the output video file.mov or mp4 (Default: mp4)
base64Indicates whether the init_image is provided in base64 format. Defaults to false.The default is false. (TRUE or FALSE)
tempIf true, stores the video in temporary storage (cleaned every 24 hours). Default is false.The default is false. (TRUE or FALSE)
webhookA URL to receive a POST API call once the video generation is complete.URL
track_idA unique ID used in the webhook response to identify the request.string
Open in Playground 🚀

Example​

Body​

When the model_id is wan2.2, the request json looks like so,

Body
{
    "key":"",
    "init_image":"https://pub-3626123a908346a7a8be8d9295f44e26.r2.dev/livewire-tmp/Vil4dkFzgFw0xyU7YsF4YqzJQXuGmr-metaNTliM2VmYTNmODE2NjdiMzljYjYzOTdlOGU5Nzg1OTAud2VicA==-.webp",
    "prompt":"moving character",
    "model_id":"wan2.2",
    "negative_prompt":"low quality",
    "resolution":320,
    "num_frames":16,
    "num_inference_steps":31,
    "guidance_scale":7,
    "sample_shift":5,
    "output_type":"mp4",
    "webhook": null,
    "track_id":null
}

When the model_id is wan2.1, the request json looks like so,

Body
{
    "key":"",
    "init_image":"https://pub-3626123a908346a7a8be8d9295f44e26.r2.dev/livewire-tmp/Vil4dkFzgFw0xyU7YsF4YqzJQXuGmr-metaNTliM2VmYTNmODE2NjdiMzljYjYzOTdlOGU5Nzg1OTAud2VicA==-.webp",
    "prompt":"moving character",
    "model_id":"wan2.1",
    "negative_prompt":"low quality",
    "resolution":320,
    "num_frames":16,
    "num_inference_steps":31,
    "guidance_scale":7,
    "sample_shift":5,
    "output_type":"mp4",
    "webhook": null,
    "track_id":null
}

Request​

var myHeaders = new Headers();
myHeaders.append("Content-Type", "application/json");

var raw = JSON.stringify({
    "key":"",
    "init_image":"https://pub-3626123a908346a7a8be8d9295f44e26.r2.dev/livewire-tmp/Vil4dkFzgFw0xyU7YsF4YqzJQXuGmr-metaNTliM2VmYTNmODE2NjdiMzljYjYzOTdlOGU5Nzg1OTAud2VicA==-.webp",
    "prompt":"moving character",
    "model_id":"wan2.2",
    "negative_prompt":"low quality",
    "resolution":480,
    "num_frames":81,
    "num_inference_steps":30,
    "guidance_scale": 5.0,
    "sample_shift":5,
    "fps":16,
    "output_type":"mp4",
    "webhook": null,
    "track_id":null
});

var requestOptions = {
  method: 'POST',
  headers: myHeaders,
  body: raw,
  redirect: 'follow'
};

fetch("https://modelslab.com/api/v6/video/img2video_ultra", requestOptions)
  .then(response => response.text())
  .then(result => console.log(result))
  .catch(error => console.log('error', error));

Response​

{
    "status": "success",
    "generationTime": 4.49,
    "id": 147,
    "output": [
        "https://modelslab-bom.s3.amazonaws.com/generations/9faea114-b3e5-4960-b0de-cc27b8f2efa0.mp4"
    ],
    "proxy_links": [
        "https://modelslab-bom.s3.amazonaws.com/generations/9faea114-b3e5-4960-b0de-cc27b8f2efa0.mp4"
    ],
    "meta": {
        "base64": "no",
        "file_prefix": "a51498bf-0eee-44c5-a473-81cc867b288a",
        "fps": 16,
        "guidance_scale": 5,
        "id": null,
        "instant_response": "no",
        "negative_prompt": "low quality",
        "num_frames": 81,
        "num_inference_steps": 30,
        "opacity": 0.8,
        "output_type": "mp4",
        "padding_down": 10,
        "padding_right": 10,
        "portrait": "no",
        "prompt": "moving character",
        "init_image": "https://pub-3626123a908346a7a8be8d9295f44e26.r2.dev/livewire-tmp/aMjqB1jtIwQF9uYqwPtSIvOepd7g1u-metaY2NkMzBhMmIxOTFlNmIyZDk0Y2JjYzYyMTIxYTYwN2QuanBn-.jpg",
        "model_id": "wan2.2",
        "rescale": "yes",
        "resolution": 480,
        "sample_shift": 5,
        "scale_down": 6,
        "seed": 3644269522,
        "temp": "no",
        "track_id": null,
        "watermark": "no",
        "webhook": null
    },
    "future_links": [
        "https://modelslab-bom.s3.amazonaws.com/generations/09e6f35f-2a47-4271-82a5-9cfff8bbc43a.mp4"
    ]
}