Versions
Failed to load versions. Head to the versions page to see all versions for this model.
You're looking at a specific version of this model. Jump to the model overview.
lucataco /hunyuanvideo:2b1add9b
Input
Run this model in Node.js with one line of code:
npx create-replicate --model=lucataco/hunyuanvideo
or set up a project from scratch
Install Replicate’s Node.js client library:
npm install replicateSet 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 lucataco/hunyuanvideo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"lucataco/hunyuanvideo:2b1add9b58a0ff73fd7ff82407246c42c603d82234917bc65a4f84b45a154f92",
{
input: {
fps: 15,
seed: 0,
width: 960,
height: 544,
prompt: "A cat walks on the grass, realistic",
num_frames: 61,
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 replicateSet 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 replicateRun lucataco/hunyuanvideo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"lucataco/hunyuanvideo:2b1add9b58a0ff73fd7ff82407246c42c603d82234917bc65a4f84b45a154f92",
input={
"fps": 15,
"seed": 0,
"width": 960,
"height": 544,
"prompt": "A cat walks on the grass, realistic",
"num_frames": 61,
"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 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:2b1add9b58a0ff73fd7ff82407246c42c603d82234917bc65a4f84b45a154f92",
"input": {
"fps": 15,
"seed": 0,
"width": 960,
"height": 544,
"prompt": "A cat walks on the grass, realistic",
"num_frames": 61,
"guidance_scale": 6,
"num_inference_steps": 30
}
}' \
https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Add a payment method to run this model.
Sign in with GitHub
By signing in, you agree to our
terms of service and privacy policy
Output
{
"completed_at": "2024-12-29T18:18:04.030606Z",
"created_at": "2024-12-29T18:13:18.989000Z",
"data_removed": false,
"error": null,
"id": "sd12q4ay1nrme0cm2eftj4fker",
"input": {
"fps": 15,
"seed": 0,
"width": 960,
"height": 544,
"prompt": "A cat walks on the grass, realistic",
"num_frames": 61,
"guidance_scale": 6,
"num_inference_steps": 30
},
"logs": "Using seed: 33329\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:08<03:54, 8.07s/it]\n 7%|▋ | 2/30 [00:13<03:08, 6.75s/it]\n 10%|█ | 3/30 [00:21<03:16, 7.28s/it]\n 13%|█▎ | 4/30 [00:29<03:15, 7.54s/it]\n 17%|█▋ | 5/30 [00:37<03:11, 7.68s/it]\n 20%|██ | 6/30 [00:45<03:06, 7.75s/it]\n 23%|██▎ | 7/30 [00:53<02:59, 7.80s/it]\n 27%|██▋ | 8/30 [01:01<02:52, 7.82s/it]\n 30%|███ | 9/30 [01:09<02:44, 7.84s/it]\n 33%|███▎ | 10/30 [01:17<02:37, 7.86s/it]\n 37%|███▋ | 11/30 [01:24<02:29, 7.86s/it]\n 40%|████ | 12/30 [01:32<02:21, 7.87s/it]\n 43%|████▎ | 13/30 [01:40<02:13, 7.88s/it]\n 47%|████▋ | 14/30 [01:48<02:06, 7.88s/it]\n 50%|█████ | 15/30 [01:56<01:58, 7.88s/it]\n 53%|█████▎ | 16/30 [02:04<01:50, 7.88s/it]\n 57%|█████▋ | 17/30 [02:12<01:42, 7.88s/it]\n 60%|██████ | 18/30 [02:20<01:34, 7.88s/it]\n 63%|██████▎ | 19/30 [02:28<01:26, 7.88s/it]\n 67%|██████▋ | 20/30 [02:35<01:18, 7.88s/it]\n 70%|███████ | 21/30 [02:43<01:10, 7.88s/it]\n 73%|███████▎ | 22/30 [02:51<01:03, 7.88s/it]\n 77%|███████▋ | 23/30 [02:59<00:55, 7.89s/it]\n 80%|████████ | 24/30 [03:07<00:47, 7.89s/it]\n 83%|████████▎ | 25/30 [03:15<00:39, 7.89s/it]\n 87%|████████▋ | 26/30 [03:23<00:31, 7.89s/it]\n 90%|█████████ | 27/30 [03:31<00:23, 7.89s/it]\n 93%|█████████▎| 28/30 [03:39<00:15, 7.89s/it]\n 97%|█████████▋| 29/30 [03:46<00:07, 7.88s/it]\n100%|██████████| 30/30 [03:54<00:00, 7.89s/it]\n100%|██████████| 30/30 [03:54<00:00, 7.83s/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": 246.7395181,
"total_time": 285.041606
},
"output": "https://replicate.delivery/xezq/xTq1yeTpf8mSwkDiTVMv0zh6hcozHSrwWX6nC8e1feQiLiefJA/output.mp4",
"started_at": "2024-12-29T18:13:57.291088Z",
"status": "succeeded",
"urls": {
"stream": "https://stream.replicate.com/v1/files/bcwr-gzzgqqajc3wceuf7neps3jqjbggvmvdnqo7sj44mdvwjfsc7p2xq",
"get": "https://api.replicate.com/v1/predictions/sd12q4ay1nrme0cm2eftj4fker",
"cancel": "https://api.replicate.com/v1/predictions/sd12q4ay1nrme0cm2eftj4fker/cancel"
},
"version": "2b1add9b58a0ff73fd7ff82407246c42c603d82234917bc65a4f84b45a154f92"
}Generated in
Using seed: 33329
0%| | 0/30 [00:00<?, ?it/s]
3%|▎ | 1/30 [00:08<03:54, 8.07s/it]
7%|▋ | 2/30 [00:13<03:08, 6.75s/it]
10%|█ | 3/30 [00:21<03:16, 7.28s/it]
13%|█▎ | 4/30 [00:29<03:15, 7.54s/it]
17%|█▋ | 5/30 [00:37<03:11, 7.68s/it]
20%|██ | 6/30 [00:45<03:06, 7.75s/it]
23%|██▎ | 7/30 [00:53<02:59, 7.80s/it]
27%|██▋ | 8/30 [01:01<02:52, 7.82s/it]
30%|███ | 9/30 [01:09<02:44, 7.84s/it]
33%|███▎ | 10/30 [01:17<02:37, 7.86s/it]
37%|███▋ | 11/30 [01:24<02:29, 7.86s/it]
40%|████ | 12/30 [01:32<02:21, 7.87s/it]
43%|████▎ | 13/30 [01:40<02:13, 7.88s/it]
47%|████▋ | 14/30 [01:48<02:06, 7.88s/it]
50%|█████ | 15/30 [01:56<01:58, 7.88s/it]
53%|█████▎ | 16/30 [02:04<01:50, 7.88s/it]
57%|█████▋ | 17/30 [02:12<01:42, 7.88s/it]
60%|██████ | 18/30 [02:20<01:34, 7.88s/it]
63%|██████▎ | 19/30 [02:28<01:26, 7.88s/it]
67%|██████▋ | 20/30 [02:35<01:18, 7.88s/it]
70%|███████ | 21/30 [02:43<01:10, 7.88s/it]
73%|███████▎ | 22/30 [02:51<01:03, 7.88s/it]
77%|███████▋ | 23/30 [02:59<00:55, 7.89s/it]
80%|████████ | 24/30 [03:07<00:47, 7.89s/it]
83%|████████▎ | 25/30 [03:15<00:39, 7.89s/it]
87%|████████▋ | 26/30 [03:23<00:31, 7.89s/it]
90%|█████████ | 27/30 [03:31<00:23, 7.89s/it]
93%|█████████▎| 28/30 [03:39<00:15, 7.89s/it]
97%|█████████▋| 29/30 [03:46<00:07, 7.88s/it]
100%|██████████| 30/30 [03:54<00:00, 7.89s/it]
100%|██████████| 30/30 [03:54<00:00, 7.83s/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)