Skip to main content
POST
/
video
/
img2video
Generate video from image
curl --request POST \
  --url https://modelslab.com/api/v6/video/img2video \
  --header 'Content-Type: application/json' \
  --data '{
  "key": "<string>",
  "model_id": "svd",
  "init_image": "<string>",
  "prompt": "<string>",
  "negative_prompt": "<string>",
  "height": 123,
  "width": 123,
  "num_frames": 16,
  "num_inference_steps": 20,
  "min_guidance_scale": 1,
  "max_guidance_scale": 3,
  "motion_bucket_id": 127,
  "noise_aug_strength": 0.5,
  "fps": 15,
  "output_type": "mp4",
  "temp": false,
  "webhook": "<string>",
  "track_id": "<string>"
}'
{
  "status": "success",
  "generationTime": 123,
  "id": 123,
  "output": [
    "<string>"
  ],
  "proxy_links": [
    "<string>"
  ],
  "future_links": [
    "<string>"
  ],
  "meta": {},
  "eta": 123,
  "message": "<string>",
  "tip": "<string>",
  "fetch_result": "<string>"
}

​
Image to Video

Generate videos from images. Image to Video Example

​
Request

Make a POST request to below endpoint and pass the required parameters in the request body.
curl
--request POST 'https://modelslab.com/api/v6/video/img2video' \

​
Body

json
{
    "key":"",
    "model_id":"svd",
    "init_image": "https://imagedelivery.net/PP4qZJxMlvGLHJQBm3ErNg/e2f9cb8e-cb87-4143-dd81-a9e77e3bb800/768",
    "height":512,
    "width":512,
    "num_frames":25,
    "num_inference_steps":20,
    "min_guidance_scale":1,
    "max_guidance_scale":3,
    "motion_bucket_id":20,
    "noise_aug_strength":0.02,
    "webhook":null,
    "track_id":null
}

Body

application/json
​
key
string
required

Your API Key used for request authorization

​
model_id
enum<string>
required

The ID of the model to use

Available options:
svd
​
init_image
string<uri>
required

URL of the initial image

​
prompt
string

Text prompt describing desired video elements

​
negative_prompt
string

Items you don't want in the video

​
height
integer

Height in pixels

Required range: x <= 512
​
width
integer

Width in pixels

Required range: x <= 512
​
num_frames
integer
default:16

Number of frames

Required range: x <= 25
​
num_inference_steps
integer
default:20

Number of denoising steps

Required range: x <= 50
​
min_guidance_scale
number
default:1

Start value of guidance scale

Required range: 1 <= x <= 8
​
max_guidance_scale
number
default:3

End value of guidance scale

Required range: 1 <= x <= 8
​
motion_bucket_id
integer
default:127

Motion control parameter

​
noise_aug_strength
number

Noise augmentation strength

Required range: 0 <= x <= 1
​
fps
integer

Frames per second

Required range: x <= 16
​
output_type
enum<string>

Output format

Available options:
mp4,
gif
​
temp
boolean
default:false

Store in temporary storage

​
webhook
string<uri>

Webhook URL

​
track_id
string

Tracking ID

Response

Image-to-video generation response

​
status
enum<string>

Status of the video generation

Available options:
success,
processing,
error
​
generationTime
number

Time taken to generate the video in seconds

​
id
integer

Unique identifier for the video generation

​
output
string<uri>[]

Array of generated video URLs

​
proxy_links
string<uri>[]

Array of proxy video URLs

​
future_links
string<uri>[]

Array of future video URLs for queued requests

​
meta
object

Metadata about the video generation including all parameters used

​
eta
integer

Estimated time for completion in seconds (processing status)

​
message
string

Status message or additional information

​
tip
string

Additional information or tips for the user

​
fetch_result
string<uri>

URL to fetch the result when processing