Prediction

Model

lightricks/ltx-video-0.9.7:b1a80c6d

qmyvpkc8c1rma0cpsxe9jh7dwm

Status

Succeeded

Source

Web

Hardware

L40S

Total duration

1m 50s

Created

7 months ago

Webhook

–

Input

prompt: Cinematic tracking shot through an orange grove, weaving between branches heavy with ripe fruit. The camera glides past clusters of oranges swaying in the breeze, leaves rustling gently. Sunlight filters through the canopy, creating soft, shifting patterns of light and shadow on the fruit and foliage. The motion feels smooth and immersive, like floating through a warm, late afternoon scene.
image: https://replicate.delivery/pbxt/N0XnIwk5PobplTd9hSKlPZrGgZvwYa8ySIGAt0BQa9bgmA6y/oranges.png
negative_prompt: worst quality, inconsistent motion, blurry, jittery, distorted
width: 704
height: 480
num_frames: 161
num_inference_steps: 50
guidance_scale: 3
fps: 24

{
  "fps": 24,
  "guidance_scale": 3,
  "height": 480,
  "image": "https://replicate.delivery/pbxt/N0XnIwk5PobplTd9hSKlPZrGgZvwYa8ySIGAt0BQa9bgmA6y/oranges.png",
  "negative_prompt": "worst quality, inconsistent motion, blurry, jittery, distorted",
  "num_frames": 161,
  "num_inference_steps": 50,
  "prompt": "Cinematic tracking shot through an orange grove, weaving between branches heavy with ripe fruit. The camera glides past clusters of oranges swaying in the breeze, leaves rustling gently. Sunlight filters through the canopy, creating soft, shifting patterns of light and shadow on the fruit and foliage. The motion feels smooth and immersive, like floating through a warm, late afternoon scene.",
  "width": 704
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_YYC**********************************

This is your API token. Keep it to yourself.

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 lightricks/ltx-video-0.9.7 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lightricks/ltx-video-0.9.7:b1a80c6dbce390c23bb52aecebc0e09d445ac12136dd4dc539350c76030fc815",
  {
    input: {
      fps: 24,
      guidance_scale: 3,
      height: 480,
      image: "https://replicate.delivery/pbxt/N0XnIwk5PobplTd9hSKlPZrGgZvwYa8ySIGAt0BQa9bgmA6y/oranges.png",
      negative_prompt: "worst quality, inconsistent motion, blurry, jittery, distorted",
      num_frames: 161,
      num_inference_steps: 50,
      prompt: "Cinematic tracking shot through an orange grove, weaving between branches heavy with ripe fruit. The camera glides past clusters of oranges swaying in the breeze, leaves rustling gently. Sunlight filters through the canopy, creating soft, shifting patterns of light and shadow on the fruit and foliage. The motion feels smooth and immersive, like floating through a warm, late afternoon scene.",
      width: 704
    }
  }
);

// 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=r8_YYC**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

Run lightricks/ltx-video-0.9.7 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lightricks/ltx-video-0.9.7:b1a80c6dbce390c23bb52aecebc0e09d445ac12136dd4dc539350c76030fc815",
    input={
        "fps": 24,
        "guidance_scale": 3,
        "height": 480,
        "image": "https://replicate.delivery/pbxt/N0XnIwk5PobplTd9hSKlPZrGgZvwYa8ySIGAt0BQa9bgmA6y/oranges.png",
        "negative_prompt": "worst quality, inconsistent motion, blurry, jittery, distorted",
        "num_frames": 161,
        "num_inference_steps": 50,
        "prompt": "Cinematic tracking shot through an orange grove, weaving between branches heavy with ripe fruit. The camera glides past clusters of oranges swaying in the breeze, leaves rustling gently. Sunlight filters through the canopy, creating soft, shifting patterns of light and shadow on the fruit and foliage. The motion feels smooth and immersive, like floating through a warm, late afternoon scene.",
        "width": 704
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output.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=r8_YYC**********************************

This is your API token. Keep it to yourself.

Run lightricks/ltx-video-0.9.7 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": "lightricks/ltx-video-0.9.7:b1a80c6dbce390c23bb52aecebc0e09d445ac12136dd4dc539350c76030fc815",
    "input": {
      "fps": 24,
      "guidance_scale": 3,
      "height": 480,
      "image": "https://replicate.delivery/pbxt/N0XnIwk5PobplTd9hSKlPZrGgZvwYa8ySIGAt0BQa9bgmA6y/oranges.png",
      "negative_prompt": "worst quality, inconsistent motion, blurry, jittery, distorted",
      "num_frames": 161,
      "num_inference_steps": 50,
      "prompt": "Cinematic tracking shot through an orange grove, weaving between branches heavy with ripe fruit. The camera glides past clusters of oranges swaying in the breeze, leaves rustling gently. Sunlight filters through the canopy, creating soft, shifting patterns of light and shadow on the fruit and foliage. The motion feels smooth and immersive, like floating through a warm, late afternoon scene.",
      "width": 704
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "id": "qmyvpkc8c1rma0cpsxe9jh7dwm",
  "model": "lightricks/ltx-video-0.9.7",
  "version": "b1a80c6dbce390c23bb52aecebc0e09d445ac12136dd4dc539350c76030fc815",
  "input": {
    "fps": 24,
    "guidance_scale": 3,
    "height": 480,
    "image": "https://replicate.delivery/pbxt/N0XnIwk5PobplTd9hSKlPZrGgZvwYa8ySIGAt0BQa9bgmA6y/oranges.png",
    "negative_prompt": "worst quality, inconsistent motion, blurry, jittery, distorted",
    "num_frames": 161,
    "num_inference_steps": 50,
    "prompt": "Cinematic tracking shot through an orange grove, weaving between branches heavy with ripe fruit. The camera glides past clusters of oranges swaying in the breeze, leaves rustling gently. Sunlight filters through the canopy, creating soft, shifting patterns of light and shadow on the fruit and foliage. The motion feels smooth and immersive, like floating through a warm, late afternoon scene.",
    "width": 704
  },
  "logs": "Using seed: 39064\nOriginal inputs: width=704, height=480, num_frames=161\nProcessed inputs: width=704, height=480, num_frames=161\n[~] Using Image-to-Video pipeline\n[~] Generating video with prompt: 'Cinematic tracking shot through an orange grove, weaving between branches heavy with ripe fruit. The camera glides past clusters of oranges swaying in the breeze, leaves rustling gently. Sunlight filters through the canopy, creating soft, shifting patterns of light and shadow on the fruit and foliage. The motion feels smooth and immersive, like floating through a warm, late afternoon scene.'\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:39,  1.24it/s]\n  4%|▍         | 2/50 [00:01<00:29,  1.64it/s]\n  6%|▌         | 3/50 [00:02<00:32,  1.45it/s]\n  8%|▊         | 4/50 [00:02<00:33,  1.37it/s]\n 10%|█         | 5/50 [00:03<00:33,  1.34it/s]\n 12%|█▏        | 6/50 [00:04<00:33,  1.31it/s]\n 14%|█▍        | 7/50 [00:05<00:33,  1.30it/s]\n 16%|█▌        | 8/50 [00:05<00:32,  1.29it/s]\n 18%|█▊        | 9/50 [00:06<00:31,  1.28it/s]\n 20%|██        | 10/50 [00:07<00:31,  1.28it/s]\n 22%|██▏       | 11/50 [00:08<00:30,  1.28it/s]\n 24%|██▍       | 12/50 [00:09<00:29,  1.27it/s]\n 26%|██▌       | 13/50 [00:09<00:29,  1.27it/s]\n 28%|██▊       | 14/50 [00:10<00:28,  1.27it/s]\n 30%|███       | 15/50 [00:11<00:27,  1.27it/s]\n 32%|███▏      | 16/50 [00:12<00:26,  1.27it/s]\n 34%|███▍      | 17/50 [00:13<00:26,  1.27it/s]\n 36%|███▌      | 18/50 [00:13<00:25,  1.27it/s]\n 38%|███▊      | 19/50 [00:14<00:24,  1.27it/s]\n 40%|████      | 20/50 [00:15<00:23,  1.27it/s]\n 42%|████▏     | 21/50 [00:16<00:22,  1.26it/s]\n 44%|████▍     | 22/50 [00:17<00:22,  1.26it/s]\n 46%|████▌     | 23/50 [00:17<00:21,  1.26it/s]\n 48%|████▊     | 24/50 [00:18<00:20,  1.26it/s]\n 50%|█████     | 25/50 [00:19<00:19,  1.26it/s]\n 52%|█████▏    | 26/50 [00:20<00:19,  1.26it/s]\n 54%|█████▍    | 27/50 [00:21<00:18,  1.26it/s]\n 56%|█████▌    | 28/50 [00:21<00:17,  1.26it/s]\n 58%|█████▊    | 29/50 [00:22<00:16,  1.26it/s]\n 60%|██████    | 30/50 [00:23<00:15,  1.26it/s]\n 62%|██████▏   | 31/50 [00:24<00:15,  1.26it/s]\n 64%|██████▍   | 32/50 [00:24<00:14,  1.26it/s]\n 66%|██████▌   | 33/50 [00:25<00:13,  1.26it/s]\n 68%|██████▊   | 34/50 [00:26<00:12,  1.26it/s]\n 70%|███████   | 35/50 [00:27<00:11,  1.26it/s]\n 72%|███████▏  | 36/50 [00:28<00:11,  1.26it/s]\n 74%|███████▍  | 37/50 [00:28<00:10,  1.26it/s]\n 76%|███████▌  | 38/50 [00:29<00:09,  1.26it/s]\n 78%|███████▊  | 39/50 [00:30<00:08,  1.26it/s]\n 80%|████████  | 40/50 [00:31<00:07,  1.26it/s]\n 82%|████████▏ | 41/50 [00:32<00:07,  1.26it/s]\n 84%|████████▍ | 42/50 [00:32<00:06,  1.26it/s]\n 86%|████████▌ | 43/50 [00:33<00:05,  1.26it/s]\n 88%|████████▊ | 44/50 [00:34<00:04,  1.26it/s]\n 90%|█████████ | 45/50 [00:35<00:03,  1.26it/s]\n 92%|█████████▏| 46/50 [00:36<00:03,  1.26it/s]\n 94%|█████████▍| 47/50 [00:36<00:02,  1.26it/s]\n 96%|█████████▌| 48/50 [00:37<00:01,  1.25it/s]\n 98%|█████████▊| 49/50 [00:38<00:00,  1.25it/s]\n100%|██████████| 50/50 [00:39<00:00,  1.25it/s]\n100%|██████████| 50/50 [00:39<00:00,  1.27it/s]\n[+] Video generation complete: output.mp4",
  "output": "https://replicate.delivery/xezq/kMeeedc3N8MpVp1VqeYhwNM5fifgPjsP4YglavjpHmU1wlJLF/output.mp4",
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2025-05-14T15:14:30.112Z",
  "started_at": "2025-05-14T15:15:20.036812Z",
  "completed_at": "2025-05-14T15:16:19.728713Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/qmyvpkc8c1rma0cpsxe9jh7dwm/cancel",
    "get": "https://api.replicate.com/v1/predictions/qmyvpkc8c1rma0cpsxe9jh7dwm",
    "stream": "https://stream.replicate.com/v1/files/bcwr-ggybkgc22dcfojwds2o632ppuvu6y5i6ur4axozbylrfv7di5hva",
    "web": "https://replicate.com/p/qmyvpkc8c1rma0cpsxe9jh7dwm"
  },
  "metrics": {
    "predict_time": 59.691900125,
    "total_time": 109.616713
  }
}

Generated in

59.7 seconds

Tweak it Upscale Report

Using seed: 39064 Original inputs: width=704, height=480, num_frames=161 Processed inputs: width=704, height=480, num_frames=161 [~] Using Image-to-Video pipeline [~] Generating video with prompt: 'Cinematic tracking shot through an orange grove, weaving between branches heavy with ripe fruit. The camera glides past clusters of oranges swaying in the breeze, leaves rustling gently. Sunlight filters through the canopy, creating soft, shifting patterns of light and shadow on the fruit and foliage. The motion feels smooth and immersive, like floating through a warm, late afternoon scene.' 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:39, 1.24it/s] 4%|▍ | 2/50 [00:01<00:29, 1.64it/s] 6%|▌ | 3/50 [00:02<00:32, 1.45it/s] 8%|▊ | 4/50 [00:02<00:33, 1.37it/s] 10%|█ | 5/50 [00:03<00:33, 1.34it/s] 12%|█▏ | 6/50 [00:04<00:33, 1.31it/s] 14%|█▍ | 7/50 [00:05<00:33, 1.30it/s] 16%|█▌ | 8/50 [00:05<00:32, 1.29it/s] 18%|█▊ | 9/50 [00:06<00:31, 1.28it/s] 20%|██ | 10/50 [00:07<00:31, 1.28it/s] 22%|██▏ | 11/50 [00:08<00:30, 1.28it/s] 24%|██▍ | 12/50 [00:09<00:29, 1.27it/s] 26%|██▌ | 13/50 [00:09<00:29, 1.27it/s] 28%|██▊ | 14/50 [00:10<00:28, 1.27it/s] 30%|███ | 15/50 [00:11<00:27, 1.27it/s] 32%|███▏ | 16/50 [00:12<00:26, 1.27it/s] 34%|███▍ | 17/50 [00:13<00:26, 1.27it/s] 36%|███▌ | 18/50 [00:13<00:25, 1.27it/s] 38%|███▊ | 19/50 [00:14<00:24, 1.27it/s] 40%|████ | 20/50 [00:15<00:23, 1.27it/s] 42%|████▏ | 21/50 [00:16<00:22, 1.26it/s] 44%|████▍ | 22/50 [00:17<00:22, 1.26it/s] 46%|████▌ | 23/50 [00:17<00:21, 1.26it/s] 48%|████▊ | 24/50 [00:18<00:20, 1.26it/s] 50%|█████ | 25/50 [00:19<00:19, 1.26it/s] 52%|█████▏ | 26/50 [00:20<00:19, 1.26it/s] 54%|█████▍ | 27/50 [00:21<00:18, 1.26it/s] 56%|█████▌ | 28/50 [00:21<00:17, 1.26it/s] 58%|█████▊ | 29/50 [00:22<00:16, 1.26it/s] 60%|██████ | 30/50 [00:23<00:15, 1.26it/s] 62%|██████▏ | 31/50 [00:24<00:15, 1.26it/s] 64%|██████▍ | 32/50 [00:24<00:14, 1.26it/s] 66%|██████▌ | 33/50 [00:25<00:13, 1.26it/s] 68%|██████▊ | 34/50 [00:26<00:12, 1.26it/s] 70%|███████ | 35/50 [00:27<00:11, 1.26it/s] 72%|███████▏ | 36/50 [00:28<00:11, 1.26it/s] 74%|███████▍ | 37/50 [00:28<00:10, 1.26it/s] 76%|███████▌ | 38/50 [00:29<00:09, 1.26it/s] 78%|███████▊ | 39/50 [00:30<00:08, 1.26it/s] 80%|████████ | 40/50 [00:31<00:07, 1.26it/s] 82%|████████▏ | 41/50 [00:32<00:07, 1.26it/s] 84%|████████▍ | 42/50 [00:32<00:06, 1.26it/s] 86%|████████▌ | 43/50 [00:33<00:05, 1.26it/s] 88%|████████▊ | 44/50 [00:34<00:04, 1.26it/s] 90%|█████████ | 45/50 [00:35<00:03, 1.26it/s] 92%|█████████▏| 46/50 [00:36<00:03, 1.26it/s] 94%|█████████▍| 47/50 [00:36<00:02, 1.26it/s] 96%|█████████▌| 48/50 [00:37<00:01, 1.25it/s] 98%|█████████▊| 49/50 [00:38<00:00, 1.25it/s] 100%|██████████| 50/50 [00:39<00:00, 1.25it/s] 100%|██████████| 50/50 [00:39<00:00, 1.27it/s] [+] Video generation complete: output.mp4