lucataco/hunyuanvideo-community-lora:b3bacda0 | Run with an API on Replicate

Version

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

lucataco /hunyuanvideo-community-lora:b3bacda0

Input

prompt

string

Shift + Return to add a new line

Style of snomexut, A menacing blue tuxemon with sharp claws and fierce fangs roars against a cosmic backdrop, its body adorned with glowing orbs and sharp pink detailsStyle of snomexut, A menacing blue tuxemon with sharp claws and fierce fangs roars against a cosmic backdrop, its body adorned with glowing orbs and sharp pink details

The prompt to guide the video generation

Default: "A cat walks on the grass, realistic"

width

integer

(minimum: 512, maximum: 1280)

Width of the video in pixels

Default: 960

height

integer

(minimum: 320, maximum: 1280)

Height of the video in pixels

Default: 544

num_frames

integer

(minimum: 17, maximum: 129)

Number of frames to generate (must be 4k+1, ex: 49 or 129)

Default: 61

num_inference_steps

integer

(minimum: 1, maximum: 50)

Number of denoising steps

Default: 30

guidance_scale

number

(minimum: 1, maximum: 10)

Guidance scale

Default: 6

extra_lora

string

Shift + Return to add a new line

Extra LoRA to load

lora_scale

number

(minimum: -1, maximum: 3)

Scale for the LoRA weights

Default: 0.8

fps

integer

(minimum: 1, maximum: 30)

Frames per second of the output video

Default: 15

seed

integer

Random seed (0 for random)

Default: 0

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

npx create-replicate --model=lucataco/hunyuanvideo-community-lora

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 lucataco/hunyuanvideo-community-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/hunyuanvideo-community-lora:b3bacda053c13b8a8899d1641b2354343d576895941e5c118b90fe73e8a3bbbd",
  {
    input: {
      fps: 15,
      seed: 0,
      width: 768,
      height: 768,
      prompt: "Style of snomexut, A menacing blue tuxemon with sharp claws and fierce fangs roars against a cosmic backdrop, its body adorned with glowing orbs and sharp pink details",
      extra_lora: "a-r-r-o-w/HunyuanVideo-tuxemons",
      lora_scale: 1.2,
      num_frames: 33,
      guidance_scale: 6,
      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 lucataco/hunyuanvideo-community-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/hunyuanvideo-community-lora:b3bacda053c13b8a8899d1641b2354343d576895941e5c118b90fe73e8a3bbbd",
    input={
        "fps": 15,
        "seed": 0,
        "width": 768,
        "height": 768,
        "prompt": "Style of snomexut, A menacing blue tuxemon with sharp claws and fierce fangs roars against a cosmic backdrop, its body adorned with glowing orbs and sharp pink details",
        "extra_lora": "a-r-r-o-w/HunyuanVideo-tuxemons",
        "lora_scale": 1.2,
        "num_frames": 33,
        "guidance_scale": 6,
        "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 lucataco/hunyuanvideo-community-lora 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": "lucataco/hunyuanvideo-community-lora:b3bacda053c13b8a8899d1641b2354343d576895941e5c118b90fe73e8a3bbbd",
    "input": {
      "fps": 15,
      "seed": 0,
      "width": 768,
      "height": 768,
      "prompt": "Style of snomexut, A menacing blue tuxemon with sharp claws and fierce fangs roars against a cosmic backdrop, its body adorned with glowing orbs and sharp pink details",
      "extra_lora": "a-r-r-o-w/HunyuanVideo-tuxemons",
      "lora_scale": 1.2,
      "num_frames": 33,
      "guidance_scale": 6,
      "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": "2025-01-06T23:41:51.222663Z",
  "created_at": "2025-01-06T23:38:34.399000Z",
  "data_removed": false,
  "error": null,
  "id": "45s03pr63xrm80cm7qyb4ms7dr",
  "input": {
    "fps": 15,
    "seed": 0,
    "width": 768,
    "height": 768,
    "prompt": "Style of snomexut, A menacing blue tuxemon with sharp claws and fierce fangs roars against a cosmic backdrop, its body adorned with glowing orbs and sharp pink details",
    "extra_lora": "a-r-r-o-w/HunyuanVideo-tuxemons",
    "lora_scale": 1.2,
    "num_frames": 33,
    "guidance_scale": 6,
    "num_inference_steps": 30
  },
  "logs": "Using seed: 5496\nExtra LoRA detected\nNew LoRA detected\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:03<01:49,  3.79s/it]\n  7%|▋         | 2/30 [00:06<01:30,  3.23s/it]\n 10%|█         | 3/30 [00:10<01:31,  3.40s/it]\n 13%|█▎        | 4/30 [00:13<01:30,  3.48s/it]\n 17%|█▋        | 5/30 [00:17<01:28,  3.52s/it]\n 20%|██        | 6/30 [00:21<01:25,  3.55s/it]\n 23%|██▎       | 7/30 [00:24<01:22,  3.57s/it]\n 27%|██▋       | 8/30 [00:28<01:18,  3.58s/it]\n 30%|███       | 9/30 [00:31<01:15,  3.58s/it]\n 33%|███▎      | 10/30 [00:35<01:11,  3.58s/it]\n 37%|███▋      | 11/30 [00:39<01:08,  3.59s/it]\n 40%|████      | 12/30 [00:42<01:04,  3.59s/it]\n 43%|████▎     | 13/30 [00:46<01:01,  3.59s/it]\n 47%|████▋     | 14/30 [00:49<00:57,  3.60s/it]\n 50%|█████     | 15/30 [00:53<00:53,  3.60s/it]\n 53%|█████▎    | 16/30 [00:57<00:50,  3.60s/it]\n 57%|█████▋    | 17/30 [01:00<00:46,  3.60s/it]\n 60%|██████    | 18/30 [01:04<00:43,  3.59s/it]\n 63%|██████▎   | 19/30 [01:07<00:39,  3.60s/it]\n 67%|██████▋   | 20/30 [01:11<00:35,  3.60s/it]\n 70%|███████   | 21/30 [01:14<00:32,  3.60s/it]\n 73%|███████▎  | 22/30 [01:18<00:28,  3.60s/it]\n 77%|███████▋  | 23/30 [01:22<00:25,  3.60s/it]\n 80%|████████  | 24/30 [01:25<00:21,  3.60s/it]\n 83%|████████▎ | 25/30 [01:29<00:17,  3.60s/it]\n 87%|████████▋ | 26/30 [01:32<00:14,  3.60s/it]\n 90%|█████████ | 27/30 [01:36<00:10,  3.60s/it]\n 93%|█████████▎| 28/30 [01:40<00:07,  3.60s/it]\n 97%|█████████▋| 29/30 [01:43<00:03,  3.59s/it]\n100%|██████████| 30/30 [01:47<00:00,  3.59s/it]\n100%|██████████| 30/30 [01:47<00:00,  3.58s/it]\nhuggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n- Avoid using `tokenizers` before the fork if possible\n- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)",
  "metrics": {
    "predict_time": 158.19950779,
    "total_time": 196.823663
  },
  "output": "https://replicate.delivery/xezq/YQABKMLbskpFER2ue13qYJ8SNtxPj1tU0Heauq6waSQfhDFoA/output.mp4",
  "started_at": "2025-01-06T23:39:13.023155Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-vqilyhvbwemo6wy6kpxd2mcphyuiki3h57quxxp7uujtywkymlmq",
    "get": "https://api.replicate.com/v1/predictions/45s03pr63xrm80cm7qyb4ms7dr",
    "cancel": "https://api.replicate.com/v1/predictions/45s03pr63xrm80cm7qyb4ms7dr/cancel"
  },
  "version": "b3bacda053c13b8a8899d1641b2354343d576895941e5c118b90fe73e8a3bbbd"
}

Generated in

2 minutes 38 seconds

Tweak it ShareReport View full prediction

Using seed: 5496
Extra LoRA detected
New LoRA detected
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:03<01:49,  3.79s/it]
  7%|▋         | 2/30 [00:06<01:30,  3.23s/it]
 10%|█         | 3/30 [00:10<01:31,  3.40s/it]
 13%|█▎        | 4/30 [00:13<01:30,  3.48s/it]
 17%|█▋        | 5/30 [00:17<01:28,  3.52s/it]
 20%|██        | 6/30 [00:21<01:25,  3.55s/it]
 23%|██▎       | 7/30 [00:24<01:22,  3.57s/it]
 27%|██▋       | 8/30 [00:28<01:18,  3.58s/it]
 30%|███       | 9/30 [00:31<01:15,  3.58s/it]
 33%|███▎      | 10/30 [00:35<01:11,  3.58s/it]
 37%|███▋      | 11/30 [00:39<01:08,  3.59s/it]
 40%|████      | 12/30 [00:42<01:04,  3.59s/it]
 43%|████▎     | 13/30 [00:46<01:01,  3.59s/it]
 47%|████▋     | 14/30 [00:49<00:57,  3.60s/it]
 50%|█████     | 15/30 [00:53<00:53,  3.60s/it]
 53%|█████▎    | 16/30 [00:57<00:50,  3.60s/it]
 57%|█████▋    | 17/30 [01:00<00:46,  3.60s/it]
 60%|██████    | 18/30 [01:04<00:43,  3.59s/it]
 63%|██████▎   | 19/30 [01:07<00:39,  3.60s/it]
 67%|██████▋   | 20/30 [01:11<00:35,  3.60s/it]
 70%|███████   | 21/30 [01:14<00:32,  3.60s/it]
 73%|███████▎  | 22/30 [01:18<00:28,  3.60s/it]
 77%|███████▋  | 23/30 [01:22<00:25,  3.60s/it]
 80%|████████  | 24/30 [01:25<00:21,  3.60s/it]
 83%|████████▎ | 25/30 [01:29<00:17,  3.60s/it]
 87%|████████▋ | 26/30 [01:32<00:14,  3.60s/it]
 90%|█████████ | 27/30 [01:36<00:10,  3.60s/it]
 93%|█████████▎| 28/30 [01:40<00:07,  3.60s/it]
 97%|█████████▋| 29/30 [01:43<00:03,  3.59s/it]
100%|██████████| 30/30 [01:47<00:00,  3.59s/it]
100%|██████████| 30/30 [01:47<00:00,  3.58s/it]
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
- Avoid using `tokenizers` before the fork if possible
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)