Request

Make a POST request to below endpoint and pass the required parameters in the request body.
curl
--request POST 'https://modelslab.com/api/v1/enterprise/image_to_video_ultra/img2video' \

Body

json
{    
    "key":"",    
    "init_image":"https://pub-3626123a908346a7a8be8d9295f44e26.r2.dev/livewire-tmp/Vil4dkFzgFw0xyU7YsF4YqzJQXuGmr-metaNTliM2VmYTNmODE2NjdiMzljYjYzOTdlOGU5Nzg1OTAud2VicA==-.webp",    
    "prompt":"moving character",    
    "negative_prompt":"low quality",    
    "resolution":320,    
    "num_frames":92,    
    "num_inference_steps":8,    
    "guidance_scale":1.0,    
    "webhook": null,    
    "track_id":null
}

Body Attributes

key
string
required
Your API Key used for request authorization.
prompt
string
required
Text prompt with a description of the things you want in the video to be generated.
init_image
string
Link equivalent of a valid PNG, JPEG, or other image format file to use as initial image conditioning.
negative_prompt
string
Items you don’t want in the video.
seed
integer
Seed is used to reproduce results. The same seed will give you the same output again. Pass null for random.
resolution
number
Resolution of the generated output. Maximum is 480.
num_frames
integer
default:"92"
The number of frames in the generated video. Default is 92.
num_inference_steps
integer
default:"8"
Number of denoising steps. Required range: x <= 8
guidance_scale
number
Scale for classifier-free guidance. Min is 1.0, Max is 2.0.
fps
integer
Frames per second of the generated video. Should be less than num_frames. Maximum is 18.
portrait
boolean
default:"false"
Indicates whether the output should be in portrait mode. Accepts true or false. Default is false.
sample_shift
string
default:"3"
Controls the sampling shift in the generation process. Default is 3.
temp
boolean
default:"false"
If true, stores the video in temporary storage (cleaned every 24 hours). Default is false.
webhook
string
A URL to receive a POST API call once the video generation is complete.
track_id
string
A unique ID used in the webhook response to identify the request.