lightricks/ltx-video:983ec70a – Run with an API on Replicate

Version

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

lightricks /ltx-video:983ec70a

Input

prompt

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.

Text prompt for the video. This model needs long descriptive prompts, if the prompt is too short the quality won't be good.

Default: "best quality, 4k, HDR, a tracking shot of a beautiful scene"

negative_prompt

string

Shift + Return to add a new line

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

Things you do not want to see in your video

Default: "low quality, worst quality, deformed, distorted"

image

file

Optional input image to use as the starting frame

target_size

integer

Target size for the output video

Default: 640

aspect_ratio

string

Aspect ratio of the output video. Ignored if an image is provided.

Default: "3:2"

cfg

number

(minimum: 1, maximum: 20)

How strongly the video follows the prompt

Default: 3

steps

integer

(minimum: 1, maximum: 50)

Number of steps

Default: 30

length

integer

Length of the output video in frames

Default: 97

seed

integer

Set a seed for reproducibility. Random by default.

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

npx create-replicate --model=lightricks/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";

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

Run lightricks/ltx-video 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:983ec70a06fd872ef4c29bb6b728556fc2454125a5b2c68ab51eb8a2a9eaa46a",
  {
    input: {
      cfg: 3,
      steps: 30,
      length: 97,
      prompt: "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.",
      target_size: 640,
      aspect_ratio: "16:9",
      negative_prompt: "low quality, worst quality, deformed, distorted, watermark"
    }
  }
);

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

output = replicate.run(
    "lightricks/ltx-video:983ec70a06fd872ef4c29bb6b728556fc2454125a5b2c68ab51eb8a2a9eaa46a",
    input={
        "cfg": 3,
        "steps": 30,
        "length": 97,
        "prompt": "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.",
        "target_size": 640,
        "aspect_ratio": "16:9",
        "negative_prompt": "low quality, worst quality, deformed, distorted, watermark"
    }
)
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 lightricks/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": "lightricks/ltx-video:983ec70a06fd872ef4c29bb6b728556fc2454125a5b2c68ab51eb8a2a9eaa46a",
    "input": {
      "cfg": 3,
      "steps": 30,
      "length": 97,
      "prompt": "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.",
      "target_size": 640,
      "aspect_ratio": "16:9",
      "negative_prompt": "low quality, worst quality, deformed, distorted, watermark"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-11-29T15:39:54.145021Z",
  "created_at": "2024-11-29T15:38:29.047000Z",
  "data_removed": false,
  "error": null,
  "id": "mvk6sppn6xrma0ckf29at4ffm4",
  "input": {
    "cfg": 3,
    "steps": 30,
    "length": 97,
    "prompt": "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.",
    "target_size": 640,
    "aspect_ratio": "16:9",
    "negative_prompt": "low quality, worst quality, deformed, distorted, watermark"
  },
  "logs": "Random seed set to: 3796486662\nChecking inputs\n====================================\nRunning workflow\n[ComfyUI] got prompt\nExecuting node 44, title: Load Checkpoint, class type: CheckpointLoaderSimple\n[ComfyUI] model weight dtype torch.bfloat16, manual cast: None\n[ComfyUI] model_type FLUX\n[ComfyUI] no CLIP/text encoder weights in checkpoint, the text encoder model will not be loaded.\nExecuting node 85, title: Width and height from aspect ratio 🪴, class type: Width and height from aspect ratio 🪴\nExecuting node 84, title: EmptyLTXVLatentVideo, class type: EmptyLTXVLatentVideo\nExecuting node 71, title: LTXVScheduler, class type: LTXVScheduler\nExecuting node 73, title: KSamplerSelect, class type: KSamplerSelect\nExecuting node 38, title: Load CLIP, class type: CLIPLoader\nExecuting node 7, title: CLIP Text Encode (Negative Prompt), class type: CLIPTextEncode\n[ComfyUI] Requested to load MochiTEModel_\n[ComfyUI] Loading 1 new model\n[ComfyUI] loaded completely 0.0 9083.38671875 True\nExecuting node 6, title: CLIP Text Encode (Positive Prompt), class type: CLIPTextEncode\nExecuting node 69, title: LTXVConditioning, class type: LTXVConditioning\nExecuting node 72, title: SamplerCustom, class type: SamplerCustom\n[ComfyUI] Requested to load LTXV\n[ComfyUI] Loading 1 new model\n[ComfyUI] loaded completely 0.0 3667.902587890625 True\n[ComfyUI]\n[ComfyUI] 0%|          | 0/30 [00:00<?, ?it/s]/root/.pyenv/versions/3.10.15/lib/python3.10/site-packages/torch/functional.py:534: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3595.)\n[ComfyUI] return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]\n[ComfyUI]\n[ComfyUI] 3%|▎         | 1/30 [00:00<00:11,  2.47it/s]\n[ComfyUI] 7%|▋         | 2/30 [00:00<00:07,  3.82it/s]\n[ComfyUI] 10%|█         | 3/30 [00:00<00:07,  3.41it/s]\n[ComfyUI] 13%|█▎        | 4/30 [00:01<00:08,  3.25it/s]\n[ComfyUI] 17%|█▋        | 5/30 [00:01<00:07,  3.16it/s]\n[ComfyUI] 20%|██        | 6/30 [00:01<00:07,  3.11it/s]\n[ComfyUI] 23%|██▎       | 7/30 [00:02<00:07,  3.08it/s]\n[ComfyUI] 27%|██▋       | 8/30 [00:02<00:07,  3.06it/s]\n[ComfyUI] 30%|███       | 9/30 [00:02<00:06,  3.05it/s]\n[ComfyUI] 33%|███▎      | 10/30 [00:03<00:06,  3.04it/s]\n[ComfyUI] 37%|███▋      | 11/30 [00:03<00:06,  3.03it/s]\n[ComfyUI] 40%|████      | 12/30 [00:03<00:05,  3.02it/s]\n[ComfyUI] 43%|████▎     | 13/30 [00:04<00:05,  3.02it/s]\n[ComfyUI] 47%|████▋     | 14/30 [00:04<00:05,  3.01it/s]\n[ComfyUI] 50%|█████     | 15/30 [00:04<00:04,  3.01it/s]\n[ComfyUI] 53%|█████▎    | 16/30 [00:05<00:04,  3.01it/s]\n[ComfyUI] 57%|█████▋    | 17/30 [00:05<00:04,  3.01it/s]\n[ComfyUI] 60%|██████    | 18/30 [00:05<00:03,  3.01it/s]\n[ComfyUI] 63%|██████▎   | 19/30 [00:06<00:03,  3.00it/s]\n[ComfyUI] 67%|██████▋   | 20/30 [00:06<00:03,  3.00it/s]\n[ComfyUI] 70%|███████   | 21/30 [00:06<00:02,  3.00it/s]\n[ComfyUI] 73%|███████▎  | 22/30 [00:07<00:02,  3.00it/s]\n[ComfyUI] 77%|███████▋  | 23/30 [00:07<00:02,  3.00it/s]\n[ComfyUI] 80%|████████  | 24/30 [00:07<00:01,  3.00it/s]\n[ComfyUI] 83%|████████▎ | 25/30 [00:08<00:01,  3.00it/s]\n[ComfyUI] 87%|████████▋ | 26/30 [00:08<00:01,  3.00it/s]\n[ComfyUI] 90%|█████████ | 27/30 [00:08<00:01,  3.00it/s]\n[ComfyUI] 93%|█████████▎| 28/30 [00:09<00:00,  3.00it/s]\n[ComfyUI] 97%|█████████▋| 29/30 [00:09<00:00,  3.00it/s]\n[ComfyUI] 100%|██████████| 30/30 [00:09<00:00,  3.00it/s]\n[ComfyUI] 100%|██████████| 30/30 [00:09<00:00,  3.04it/s]\n[ComfyUI] Requested to load VideoVAE\n[ComfyUI] Loading 1 new model\nExecuting node 8, title: VAE Decode, class type: VAEDecode\n[ComfyUI] loaded completely 0.0 799.548433303833 True\nExecuting node 79, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] Prompt executed in 15.28 seconds\noutputs:  {'79': {'gifs': [{'filename': 'R8_LTX_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 25.0}]}}\n====================================\nR8_LTX_00001.png\nR8_LTX_00001.mp4",
  "metrics": {
    "predict_time": 15.426180813,
    "total_time": 85.098021
  },
  "output": [
    "https://replicate.delivery/xezq/CC1fXTLZVOxNS66XRUJLBLuAOTP6kGaXhpttZjvBijDlk86JA/R8_LTX_00001.mp4"
  ],
  "started_at": "2024-11-29T15:39:38.718840Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-tnbavyammb5mkr5wxlbpmzg6ma3yakintpv4npsss3tl7gj2rh4q",
    "get": "https://api.replicate.com/v1/predictions/mvk6sppn6xrma0ckf29at4ffm4",
    "cancel": "https://api.replicate.com/v1/predictions/mvk6sppn6xrma0ckf29at4ffm4/cancel"
  },
  "version": "983ec70a06fd872ef4c29bb6b728556fc2454125a5b2c68ab51eb8a2a9eaa46a"
}

Generated in

15.4 seconds

Tweak it ShareReport

Random seed set to: 3796486662
Checking inputs
====================================
Running workflow
[ComfyUI] got prompt
Executing node 44, title: Load Checkpoint, class type: CheckpointLoaderSimple
[ComfyUI] model weight dtype torch.bfloat16, manual cast: None
[ComfyUI] model_type FLUX
[ComfyUI] no CLIP/text encoder weights in checkpoint, the text encoder model will not be loaded.
Executing node 85, title: Width and height from aspect ratio 🪴, class type: Width and height from aspect ratio 🪴
Executing node 84, title: EmptyLTXVLatentVideo, class type: EmptyLTXVLatentVideo
Executing node 71, title: LTXVScheduler, class type: LTXVScheduler
Executing node 73, title: KSamplerSelect, class type: KSamplerSelect
Executing node 38, title: Load CLIP, class type: CLIPLoader
Executing node 7, title: CLIP Text Encode (Negative Prompt), class type: CLIPTextEncode
[ComfyUI] Requested to load MochiTEModel_
[ComfyUI] Loading 1 new model
[ComfyUI] loaded completely 0.0 9083.38671875 True
Executing node 6, title: CLIP Text Encode (Positive Prompt), class type: CLIPTextEncode
Executing node 69, title: LTXVConditioning, class type: LTXVConditioning
Executing node 72, title: SamplerCustom, class type: SamplerCustom
[ComfyUI] Requested to load LTXV
[ComfyUI] Loading 1 new model
[ComfyUI] loaded completely 0.0 3667.902587890625 True
[ComfyUI]
[ComfyUI] 0%|          | 0/30 [00:00<?, ?it/s]/root/.pyenv/versions/3.10.15/lib/python3.10/site-packages/torch/functional.py:534: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3595.)
[ComfyUI] return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
[ComfyUI]
[ComfyUI] 3%|▎         | 1/30 [00:00<00:11,  2.47it/s]
[ComfyUI] 7%|▋         | 2/30 [00:00<00:07,  3.82it/s]
[ComfyUI] 10%|█         | 3/30 [00:00<00:07,  3.41it/s]
[ComfyUI] 13%|█▎        | 4/30 [00:01<00:08,  3.25it/s]
[ComfyUI] 17%|█▋        | 5/30 [00:01<00:07,  3.16it/s]
[ComfyUI] 20%|██        | 6/30 [00:01<00:07,  3.11it/s]
[ComfyUI] 23%|██▎       | 7/30 [00:02<00:07,  3.08it/s]
[ComfyUI] 27%|██▋       | 8/30 [00:02<00:07,  3.06it/s]
[ComfyUI] 30%|███       | 9/30 [00:02<00:06,  3.05it/s]
[ComfyUI] 33%|███▎      | 10/30 [00:03<00:06,  3.04it/s]
[ComfyUI] 37%|███▋      | 11/30 [00:03<00:06,  3.03it/s]
[ComfyUI] 40%|████      | 12/30 [00:03<00:05,  3.02it/s]
[ComfyUI] 43%|████▎     | 13/30 [00:04<00:05,  3.02it/s]
[ComfyUI] 47%|████▋     | 14/30 [00:04<00:05,  3.01it/s]
[ComfyUI] 50%|█████     | 15/30 [00:04<00:04,  3.01it/s]
[ComfyUI] 53%|█████▎    | 16/30 [00:05<00:04,  3.01it/s]
[ComfyUI] 57%|█████▋    | 17/30 [00:05<00:04,  3.01it/s]
[ComfyUI] 60%|██████    | 18/30 [00:05<00:03,  3.01it/s]
[ComfyUI] 63%|██████▎   | 19/30 [00:06<00:03,  3.00it/s]
[ComfyUI] 67%|██████▋   | 20/30 [00:06<00:03,  3.00it/s]
[ComfyUI] 70%|███████   | 21/30 [00:06<00:02,  3.00it/s]
[ComfyUI] 73%|███████▎  | 22/30 [00:07<00:02,  3.00it/s]
[ComfyUI] 77%|███████▋  | 23/30 [00:07<00:02,  3.00it/s]
[ComfyUI] 80%|████████  | 24/30 [00:07<00:01,  3.00it/s]
[ComfyUI] 83%|████████▎ | 25/30 [00:08<00:01,  3.00it/s]
[ComfyUI] 87%|████████▋ | 26/30 [00:08<00:01,  3.00it/s]
[ComfyUI] 90%|█████████ | 27/30 [00:08<00:01,  3.00it/s]
[ComfyUI] 93%|█████████▎| 28/30 [00:09<00:00,  3.00it/s]
[ComfyUI] 97%|█████████▋| 29/30 [00:09<00:00,  3.00it/s]
[ComfyUI] 100%|██████████| 30/30 [00:09<00:00,  3.00it/s]
[ComfyUI] 100%|██████████| 30/30 [00:09<00:00,  3.04it/s]
[ComfyUI] Requested to load VideoVAE
[ComfyUI] Loading 1 new model
Executing node 8, title: VAE Decode, class type: VAEDecode
[ComfyUI] loaded completely 0.0 799.548433303833 True
Executing node 79, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine
[ComfyUI] Prompt executed in 15.28 seconds
outputs:  {'79': {'gifs': [{'filename': 'R8_LTX_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 25.0}]}}
====================================
R8_LTX_00001.png
R8_LTX_00001.mp4