Wan T2V 480p

The Wan2.1 14B model is an advanced text-to-video model that offers accelerated inference capabilities, enabling high-res video generation with high visual quality and motion diversity

Features

wan-2.1/t2v-480p is an open-source AI video generation model developed by Alibaba Cloud, designed for text-to-video tasks. The 14-billion-parameter professional version excels in generating complex motions and simulating physical dynamics, delivering exceptional performance.

Built upon a causal 3D Variational Autoencoder (VAE) and Video Diffusion Transformer architecture, wan-2.1/t2v-480p efficiently models spatiotemporal dependencies. In the authoritative VBench evaluation, the 14B version achieved a leading score of 86.22%, surpassing models like Sora, Luma, and Pika, and securing the top position. The model is available on Wavespeed AI, providing convenient access for developers.

Key Features

• State-of-the-Art Performance: Wan2.1 consistently outperforms existing open-source models and commercial solutions across multiple benchmarks, ensuring top-tier video generation quality.
• Consumer-Grade GPU Compatibility: The T2V-1.3B variant requires only 8.19 GB of VRAM, allowing it to run on widely available consumer-grade GPUs. For instance, it can generate a 5-second 480p video on an RTX 4090 in approximately 4 minutes without additional optimization techniques like quantization.
• Multilingual Visual Text Generation: Wan2.1 is the first video model capable of generating text in both Chinese and English within videos, enhancing its applicability in diverse linguistic contexts.
• Efficient Video VAE: The integrated video variational autoencoder (VAE) efficiently encodes and decodes 1080p videos of any length while preserving temporal information, serving as a robust foundation for video and image generation.

ComfyUI

wan-2.1/t2v-480p-lora is also available on ComfyUI, providing local inference capabilities through a node-based workflow, ensuring flexible and efficient image generation on your system.

Limitations

• Creative Focus: Wan-2.1/T2V-480p is designed for creative video synthesis from text and is not intended for generating factually accurate or reliable content.
• Inherent Biases: As with any data-driven model, outputs may reflect biases present in the training data.
• Input Sensitivity: The quality and consistency of generated videos depend significantly on the quality of the input text; subtle variations may lead to output variability.
• Resolution Limitation: This model is optimized for 480p video generation and does not support higher resolutions like 720p.

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/wan-2.1/t2v-480p" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "prompt": "A cool street dancer, wearing a baggy hoodie and hip-hop pants, dancing in front of a graffiti wall, night neon background, quick camera cuts, urban trends.",
    "negative_prompt": "",
    "size": "832*480",
    "num_inference_steps": 30,
    "duration": 5,
    "guidance_scale": 5,
    "flow_shift": 3,
    "seed": -1,
    "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