Hunyuan T2V

Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability. This endpoint generates videos from text descriptions.

Features

Hunyuan-Video/T2V is a state-of-the-art text-to-video generation model developed by Tencent, now available in collaboration with WaveSpeedAI. It transforms natural language prompts into high-quality videos with realistic motion and visual fidelity.

Key Features

• High-Quality Video Generation: Produces videos with realistic motion and visual fidelity.
• Flexible Aspect Ratios and Resolutions: Supports various video dimensions to suit different needs.
• Advanced Prompt Handling: Utilizes a built-in prompt rewrite system for improved text interpretation.
• Stable Motion and Temporal Consistency: Ensures coherent motion and scene transitions throughout the video.

ComfyUI

hunyuan-video/t2v is also available on ComfyUI, providing local inference capabilities through a node-based workflow. This ensures flexible and efficient video generation on your system, catering to various creative workflows.

Limitations

• Increased Generation Time: Longer videos or higher resolutions may result in longer processing times.
• High GPU Memory Requirements: Generating high-resolution videos may require substantial GPU memory.
• Complex Motion Challenges: Some intricate motions may necessitate careful prompt engineering for optimal results.

Out-of-Scope Use

The model and its derivatives may not be used in any way that violates applicable national, federal, state, local, or international law or regulation, including but not limited to:

• Exploiting, harming, or attempting to exploit or harm minors, including solicitation, creation, acquisition, or dissemination of child exploitative content.
• Generating or disseminating verifiably false information with the intent to harm others.
• Creating or distributing personal identifiable information that could be used to harm an individual.
• Harassing, abusing, threatening, stalking, or bullying individuals or groups.
• Producing non-consensual nudity or illegal pornographic content.
• Making fully automated decisions that adversely affect an individual’s legal rights or create binding obligations.
• Facilitating large-scale disinformation campaigns.

Accelerated Inference

Our accelerated inference approach leverages advanced optimization technology from WavespeedAI. This innovative fusion technique significantly reduces computational overhead and latency, enabling rapid image generation without compromising quality. The entire system is designed to efficiently handle large-scale inference tasks while ensuring that real-time applications achieve an optimal balance between speed and accuracy. For further details, please refer to the blog post.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/hunyuan-video/t2v" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "prompt": "A playful, fluffy orange kitten wearing sunglasses skateboarding smoothly through a neon-lit futuristic cityscape at night, passing robots, flying cars, and holographic advertisements.",
    "size": "1280*720",
    "seed": -1,
    "num_inference_steps": 30,
    "enable_safety_checker": true
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Query Parameters

Result Request Parameters

Result Response Parameters