POST
/
image-to-video
import { Livepeer } from "@livepeer/ai";
import { openAsBlob } from "node:fs";

const livepeer = new Livepeer({
  httpBearer: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await livepeer.generate.imageToVideo({
    image: await openAsBlob("example.file"),
    modelId: "",
    height: 576,
    width: 1024,
    fps: 6,
    motionBucketId: 127,
    noiseAugStrength: 0.02,
    safetyCheck: true,
    numInferenceSteps: 25,
  });

  // Handle the result
  console.log(result);
}

run();
{
  "images": [
    {
      "url": "<string>",
      "seed": 123,
      "nsfw": true
    }
  ]
}

The default Gateway used in this guide is the public Livepeer.cloud Gateway. It is free to use but not intended for production-ready applications. For production-ready applications, consider using the Livepeer Studio Gateway, which requires an API token. Alternatively, you can set up your own Gateway node or partner with one via the ai-video channel on Discord.

Please note that the exact parameters, default values, and responses may vary between models. For more information on model-specific parameters, please refer to the respective model documentation available in the image-to-video pipeline. Not all parameters might be available for a given model.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

multipart/form-data
​
image
file
required

Uploaded image to generate a video from.

​
model_id
string
default:
required

Hugging Face model ID used for video generation.

​
height
integer
default:
576

The height in pixels of the generated video.

​
width
integer
default:
1024

The width in pixels of the generated video.

​
fps
integer
default:
6

The frames per second of the generated video.

​
motion_bucket_id
integer
default:
127

Used for conditioning the amount of motion for the generation. The higher the number the more motion will be in the video.

​
noise_aug_strength
number
default:
0.02

Amount of noise added to the conditioning image. Higher values reduce resemblance to the conditioning image and increase motion.

​
safety_check
boolean
default:
true

Perform a safety check to estimate if generated images could be offensive or harmful.

​
seed
integer

Seed for random number generation.

​
num_inference_steps
integer
default:
25

Number of denoising steps. More steps usually lead to higher quality images but slower inference. Modulated by strength.

Response

200
application/json
Successful Response

Response model for image generation.

​
images
object[]
required

The generated images.

Was this page helpful?

Suggest editsRaise issue
Image To TextSegment Anything 2