Image to Video - ModelsLab

Make sure you add your s3 details for the ltx_2_3 server, so you can receive the video generated in your bucket. Videos generated without s3 details being added will be deleted after 24 hours.

This endpoint animates one still image. init_image is accepted either as a plain URL string or as a one element list — both shapes reach the same result. The prompt is optional here: the image already carries the shot, so a prompt only steers the motion.

Request

Make a POST request to below endpoint and pass the required parameters as a request body.

curl

--request POST 'https://modelslab.com/api/v1/enterprise/ltx_2_3/img2video' \

Body

json

{
  "key": "enterprise_api_key",
  "prompt": "the waves rise as the camera drifts forward",
  "init_image": "https://assets.modelslab.ai/generations/still-frame.png",
  "resolution": "16:9",
  "duration": 5,
  "num_frames": 81,
  "num_inference_steps": 4,
  "output_type": "mp4",
  "seed": null,
  "watermark": "no",
  "instant_response": false,
  "temp": false,
  "base64": false,
  "webhook": null,
  "track_id": null
}

Body Attributes

string

required

Your API Key used for request authorization.

string

required

The image to animate, as a URL or — with base64 set to true — as a base64 string. A one element list is also accepted. Only one image is used.

string

Text prompt describing the motion you want in the generated video. Optional, because the image already carries the shot.

string

default:"16:9"

Aspect ratio of the generated video, not a pixel size. options: 1:1, 16:9 or 9:16. Any other value is refused.

number

default:"5"

Length of the generated video in seconds. Minimum is 5, maximum is 12.

number

default:"81"

The number of frames in the generated video. Maximum is 81, which is also the default.

number

default:"4"

Number of denoising steps. LTX 2.3 is distilled to generate in 4 steps, so raising this costs time without adding much detail. Minimum is 1, maximum is 50.

string

default:"mp4"

Format of the generated video. options: mp4 or gif.

string

Optional model identifier forwarded to your server. Your LTX 2.3 container serves one model, so this can be left out.

number

Seed is used to reproduce results. The same seed will give you the same video again. Pass null for a random number.

string

default:"no"

Whether to watermark the generated video. options: yes or no.

boolean

default:"false"

Queue response instantly before processing finishes instead of waiting a minimum amount of time. default: false, options: true or false.

boolean

default:"false"

If true, stores the video in temporary storage which is cleaned every 24 hours. default: false, options: true or false.

boolean

default:"false"

Set to true when init_image is a base64 string instead of a URL. The two must agree: a base64 string sent with base64 false, or a URL sent with base64 true, is refused. default: false, options: true or false.

string

Set a URL to get a POST API call once the video generation is complete.

string

This ID is returned in the response to the webhook API call. This will be used to identify the webhook request.

​Request

​Body

​Body Attributes

Request

Body

Body Attributes