georgedavila/cog-ltx-video:807fb8df | Run with an API on Replicate

Version

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

georgedavila /cog-ltx-video:807fb8df

Input

myprompt

string

Shift + Return to add a new line

A chef prepares food in a professional kitchen. He has olive skin and dark, close-cropped hair, wearing traditional white chef's attire. Steam rises from the pan he's working with. The kitchen's stainless steel surfaces reflect the bright overhead lighting. The camera follows his hands as he cooks. The scene appears to be real-life footage.A chef prepares food in a professional kitchen. He has olive skin and dark, close-cropped hair, wearing traditional white chef's attire. Steam rises from the pan he's working with. The kitchen's stainless steel surfaces reflect the bright overhead lighting. The camera follows his hands as he cooks. The scene appears to be real-life footage.

Input prompt

Default: "A woman with long brown hair and light skin smiles at another woman with long blonde hair. The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek. The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage"

negative_prompt

string

Shift + Return to add a new line

low quality, worst quality, deformed, distorted, watermarklow quality, worst quality, deformed, distorted, watermark

Negative Prompt

Default: "watermark, text, deformed, worst quality, inconsistent motion, blurry, jittery, distorted"

outWidth

integer

(minimum: 128, maximum: 2048)

width of output

Default: 768

outHeight

integer

(minimum: 128, maximum: 2048)

height of output

Default: 512

guidanceScale

number

(minimum: 1, 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: 4)

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

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/cog-ltx-video

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

const output = await replicate.run(
  "georgedavila/cog-ltx-video:807fb8dfd1a0e77faed3e56dc11a0cfdd7433e4f35fb8ee7abe5abbafd27e189",
  {
    input: {
      outFPS: 24,
      myprompt: "A chef prepares food in a professional kitchen. He has olive skin and dark, close-cropped hair, wearing traditional white chef's attire. Steam rises from the pan he's working with. The kitchen's stainless steel surfaces reflect the bright overhead lighting. The camera follows his hands as he cooks. The scene appears to be real-life footage.",
      outWidth: 864,
      outHeight: 480,
      num_frames: 97,
      num_outputs: 1,
      guidanceScale: 3,
      negative_prompt: "low quality, worst quality, deformed, distorted, watermark",
      num_inference_steps: 30
    }
  }
);

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

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

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

output = replicate.run(
    "georgedavila/cog-ltx-video:807fb8dfd1a0e77faed3e56dc11a0cfdd7433e4f35fb8ee7abe5abbafd27e189",
    input={
        "outFPS": 24,
        "myprompt": "A chef prepares food in a professional kitchen. He has olive skin and dark, close-cropped hair, wearing traditional white chef's attire. Steam rises from the pan he's working with. The kitchen's stainless steel surfaces reflect the bright overhead lighting. The camera follows his hands as he cooks. The scene appears to be real-life footage.",
        "outWidth": 864,
        "outHeight": 480,
        "num_frames": 97,
        "num_outputs": 1,
        "guidanceScale": 3,
        "negative_prompt": "low quality, worst quality, deformed, distorted, watermark",
        "num_inference_steps": 30
    }
)
print(output)

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/cog-ltx-video 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/cog-ltx-video:807fb8dfd1a0e77faed3e56dc11a0cfdd7433e4f35fb8ee7abe5abbafd27e189",
    "input": {
      "outFPS": 24,
      "myprompt": "A chef prepares food in a professional kitchen. He has olive skin and dark, close-cropped hair, wearing traditional white chef\'s attire. Steam rises from the pan he\'s working with. The kitchen\'s stainless steel surfaces reflect the bright overhead lighting. The camera follows his hands as he cooks. The scene appears to be real-life footage.",
      "outWidth": 864,
      "outHeight": 480,
      "num_frames": 97,
      "num_outputs": 1,
      "guidanceScale": 3,
      "negative_prompt": "low quality, worst quality, deformed, distorted, watermark",
      "num_inference_steps": 30
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-01-10T00:19:43.347815Z",
  "created_at": "2025-01-10T00:10:33.433000Z",
  "data_removed": false,
  "error": null,
  "id": "gtnc7qk2b5rma0cm9p6ba4vsy0",
  "input": {
    "outFPS": 24,
    "myprompt": "A chef prepares food in a professional kitchen. He has olive skin and dark, close-cropped hair, wearing traditional white chef's attire. Steam rises from the pan he's working with. The kitchen's stainless steel surfaces reflect the bright overhead lighting. The camera follows his hands as he cooks. The scene appears to be real-life footage.",
    "outWidth": 864,
    "outHeight": 480,
    "num_frames": 97,
    "num_outputs": 1,
    "guidanceScale": 3,
    "negative_prompt": "low quality, worst quality, deformed, distorted, watermark",
    "num_inference_steps": 30
  },
  "logs": "Using seed: 36320\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:14,  2.01it/s]\n  7%|▋         | 2/30 [00:00<00:10,  2.68it/s]\n 10%|█         | 3/30 [00:01<00:11,  2.38it/s]\n 13%|█▎        | 4/30 [00:01<00:11,  2.26it/s]\n 17%|█▋        | 5/30 [00:02<00:11,  2.19it/s]\n 20%|██        | 6/30 [00:02<00:11,  2.16it/s]\n 23%|██▎       | 7/30 [00:03<00:10,  2.13it/s]\n 27%|██▋       | 8/30 [00:03<00:10,  2.12it/s]\n 30%|███       | 9/30 [00:04<00:09,  2.11it/s]\n 33%|███▎      | 10/30 [00:04<00:09,  2.10it/s]\n 37%|███▋      | 11/30 [00:05<00:09,  2.10it/s]\n 40%|████      | 12/30 [00:05<00:08,  2.09it/s]\n 43%|████▎     | 13/30 [00:06<00:08,  2.09it/s]\n 47%|████▋     | 14/30 [00:06<00:07,  2.09it/s]\n 50%|█████     | 15/30 [00:07<00:07,  2.09it/s]\n 53%|█████▎    | 16/30 [00:07<00:06,  2.09it/s]\n 57%|█████▋    | 17/30 [00:07<00:06,  2.08it/s]\n 60%|██████    | 18/30 [00:08<00:05,  2.08it/s]\n 63%|██████▎   | 19/30 [00:08<00:05,  2.08it/s]\n 67%|██████▋   | 20/30 [00:09<00:04,  2.08it/s]\n 70%|███████   | 21/30 [00:09<00:04,  2.08it/s]\n 73%|███████▎  | 22/30 [00:10<00:03,  2.08it/s]\n 77%|███████▋  | 23/30 [00:10<00:03,  2.08it/s]\n 80%|████████  | 24/30 [00:11<00:02,  2.08it/s]\n 83%|████████▎ | 25/30 [00:11<00:02,  2.08it/s]\n 87%|████████▋ | 26/30 [00:12<00:01,  2.08it/s]\n 90%|█████████ | 27/30 [00:12<00:01,  2.08it/s]\n 93%|█████████▎| 28/30 [00:13<00:00,  2.08it/s]\n 97%|█████████▋| 29/30 [00:13<00:00,  2.08it/s]\n100%|██████████| 30/30 [00:14<00:00,  2.08it/s]\n100%|██████████| 30/30 [00:14<00:00,  2.11it/s]",
  "metrics": {
    "predict_time": 16.597149806,
    "total_time": 549.914815
  },
  "output": "https://replicate.delivery/xezq/xUEUpDETrewoPSk04iCxBwytACHlcABIumKlojLC8A7PzwBKA/output.mp4",
  "started_at": "2025-01-10T00:19:26.750665Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-zmhg4c42ccaa3prbrpsbbhah4ktvxc6xksbgloqepvpityn73hoq",
    "get": "https://api.replicate.com/v1/predictions/gtnc7qk2b5rma0cm9p6ba4vsy0",
    "cancel": "https://api.replicate.com/v1/predictions/gtnc7qk2b5rma0cm9p6ba4vsy0/cancel"
  },
  "version": "807fb8dfd1a0e77faed3e56dc11a0cfdd7433e4f35fb8ee7abe5abbafd27e189"
}

Generated in

16.6 seconds

Tweak it Share Report