Official

wavespeedai / hunyuan-video-fast

Accelerated inference for HunyuanVideo with high resolution (1280x720), a state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions

Public
4.9K runs
$0.20 per second of video
GitHub
Weights
Paper
License

Playground Examples README

Input

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

npx create-replicate --model=wavespeedai/hunyuan-video-fast

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

const input = {
  length: 5,
  prompt: "Dynamic shot racing alongside a steam locomotive on mountain tracks, camera panning from wheels to steam billowing against snow-capped peaks. Epic scale, dramatic lighting, photorealistic detail."
};

const output = await replicate.run("wavespeedai/hunyuan-video-fast", { input });

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

output = replicate.run(
    "wavespeedai/hunyuan-video-fast",
    input={
        "length": 5,
        "prompt": "Dynamic shot racing alongside a steam locomotive on mountain tracks, camera panning from wheels to steam billowing against snow-capped peaks. Epic scale, dramatic lighting, photorealistic detail."
    }
)
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 wavespeedai/hunyuan-video-fast 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 $'{
    "input": {
      "length": 5,
      "prompt": "Dynamic shot racing alongside a steam locomotive on mountain tracks, camera panning from wheels to steam billowing against snow-capped peaks. Epic scale, dramatic lighting, photorealistic detail."
    }
  }' \
  https://api.replicate.com/v1/models/wavespeedai/hunyuan-video-fast/predictions

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

Output

Generated in

68.3 seconds

Tweak it ShareReport

Examples

View more examples

Pricing

This model is priced by how many seconds of video are generated.

Type	Per unit	Per $1
Output	$0.20 / second of video or 5 seconds of video / $1

For example, generating 100 seconds of video should cost around $20.00.

Check out our docs for more information about how per second of video pricing works on Replicate.

Readme

Accelerated Inference for HunyuanVideo with High Resolution (1280x720)

We are WaveSpeedAI, providing highly-optimized inference optimization for generative AI models.

We are excited to introduce our new product, a highly-optimized inference endpoint for HunyuanVideo model, a state-of-the-art text-to-video generation model capable of creating high-quality videos with realistic motion from text descriptions.

We utilize cutting-edge inference acceleration techniques to provide very fast inference for this model. And we are happy to bring this to you together with Replicate and DataCrunch.

Model Description ✨

This model is trained on a spatial-temporally compressed latent space and uses a large language model for text encoding. According to professional human evaluation results, HunyuanVideo outperforms previous state-of-the-art models in terms of text alignment, motion quality, and visual quality.

Key features:

🎨 High-quality video generation from text descriptions
📐 Support for various aspect ratios and resolutions
✍️ Advanced prompt handling with a built-in rewrite system
🎯 Stable motion generation and temporal consistency

Predictions Examples 💫

The model works well for prompts like: - “A cat walks on the grass, realistic style” - “A drone shot of mountains at sunset” - “A flower blooming in timelapse”

Limitations ⚠️

Generation time increases with video length and resolution
Higher resolutions require more GPU memory
Some complex motions may require prompt engineering for best results

Citation 📚

If you use this model in your research, please cite:

@misc{kong2024hunyuanvideo,
      title={HunyuanVideo: A Systematic Framework For Large Video Generative Models}, 
      author={Weijie Kong, et al.},
      year={2024},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}