georgedavila/ltx-img2vid:a2a3890f | Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

georgedavila /ltx-img2vid:a2a3890f

Playground API

Input

imageSource

file

Source Image

Default: "https://upload.wikimedia.org/wikipedia/en/4/42/Beatles_-_Abbey_Road.jpg"

myprompt

string

Shift + Return to add a new line

Four men walk across a London crosswalk. The men casually and calmly walk to the right. The scene is sunny with bright warm lighting. No cars move in the background. The camera remains stationary. Real footage.Four men walk across a London crosswalk. The men casually and calmly walk to the right. The scene is sunny with bright warm lighting. No cars move in the background. The camera remains stationary. Real footage.

Input prompt, should follow from your source image.

Default: "Four men walk across a London crosswalk. The men casually and calmly walk to the right. The scene is sunny with bright warm lighting. No cars move in the background. The camera remains stationary. Real footage."

negative_prompt

string

Shift + Return to add a new line

low quality, worst quality, inconsistent motion, blurry, jittery, distortedlow quality, worst quality, inconsistent motion, blurry, jittery, distorted

Negative Prompt

Default: "low quality, worst quality, inconsistent motion, blurry, jittery, distorted"

outWidth

integer

(minimum: 128, maximum: 2048)

width of output

Default: 864

outHeight

integer

(minimum: 128, maximum: 2048)

height of output

Default: 480

guidanceScale

number

(minimum: 0, maximum: 10)

Guidance scale (influence of input text on generation)

Default: 3

num_frames

integer

Number of images to output.

Default: 97

num_outputs

integer

(minimum: 1, maximum: 8)

Number of outputs.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

outFPS

integer

Output FPS

Default: 24

decodeTimestepParam

number

(minimum: 0.005, maximum: 1)

decodeTimestepParam

Default: 0.03

decodeNoiseScaleParam

number

(minimum: 0.0005, maximum: 1)

decodeNoiseScaleParam

Default: 0.025

seed

integer

Random seed. Leave blank to randomize the seed

Run this model in Node.js with one line of code:

npx create-replicate --model=georgedavila/ltx-img2vid

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run georgedavila/ltx-img2vid using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "georgedavila/ltx-img2vid:a2a3890f9fa7413af11e376b3f2805bf1598009e3b027f3d943350460a0d2dce",
  {
    input: {
      outFPS: 24,
      myprompt: "Four men walk across a London crosswalk. The men casually and calmly walk to the right. The scene is sunny with bright warm lighting. No cars move in the background. The camera remains stationary. Real footage.",
      outWidth: 864,
      outHeight: 480,
      num_frames: 97,
      imageSource: "https://upload.wikimedia.org/wikipedia/en/4/42/Beatles_-_Abbey_Road.jpg",
      num_outputs: 1,
      guidanceScale: 3,
      negative_prompt: "low quality, worst quality, inconsistent motion, blurry, jittery, distorted",
      decodeTimestepParam: 0.03,
      num_inference_steps: 50,
      decodeNoiseScaleParam: 0.025
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run georgedavila/ltx-img2vid using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "georgedavila/ltx-img2vid:a2a3890f9fa7413af11e376b3f2805bf1598009e3b027f3d943350460a0d2dce",
    input={
        "outFPS": 24,
        "myprompt": "Four men walk across a London crosswalk. The men casually and calmly walk to the right. The scene is sunny with bright warm lighting. No cars move in the background. The camera remains stationary. Real footage.",
        "outWidth": 864,
        "outHeight": 480,
        "num_frames": 97,
        "imageSource": "https://upload.wikimedia.org/wikipedia/en/4/42/Beatles_-_Abbey_Road.jpg",
        "num_outputs": 1,
        "guidanceScale": 3,
        "negative_prompt": "low quality, worst quality, inconsistent motion, blurry, jittery, distorted",
        "decodeTimestepParam": 0.03,
        "num_inference_steps": 50,
        "decodeNoiseScaleParam": 0.025
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run georgedavila/ltx-img2vid using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "georgedavila/ltx-img2vid:a2a3890f9fa7413af11e376b3f2805bf1598009e3b027f3d943350460a0d2dce",
    "input": {
      "outFPS": 24,
      "myprompt": "Four men walk across a London crosswalk. The men casually and calmly walk to the right. The scene is sunny with bright warm lighting. No cars move in the background. The camera remains stationary. Real footage.",
      "outWidth": 864,
      "outHeight": 480,
      "num_frames": 97,
      "imageSource": "https://upload.wikimedia.org/wikipedia/en/4/42/Beatles_-_Abbey_Road.jpg",
      "num_outputs": 1,
      "guidanceScale": 3,
      "negative_prompt": "low quality, worst quality, inconsistent motion, blurry, jittery, distorted",
      "decodeTimestepParam": 0.03,
      "num_inference_steps": 50,
      "decodeNoiseScaleParam": 0.025
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

No output yet! Press "Submit" to start a prediction.