Wan I2V 720p LoRA

Wan-2.1 i2v model with LoRA, generate high-quality videos with superior visual quality and motion diversity

Features

wan-2.1/i2v-720p-lora is a highly-optimized inference endpoint built on Wan2.1—a 14B open and advanced large-scale video generative model.LoRA stands for Low-Rank Adaptation, a technique for efficiently fine-tuning pre-trained models to generate videos with specified effects from reference images. Developed by Aliyun, and available on Wavespeed AI , this model pushes the boundaries of video generation by converting images into 480P videos with remarkable speed and efficiency.

Key Features

• High-Resolution Video Output: Precisely engineered to convert images into crisp 720p videos, ensuring exceptional visual quality and smooth motion.
• LoRA-Enhanced Performance: The integration of LoRA fusion technology enhances image detail and motion dynamics, delivering superior quality videos with enriched visual nuances.
• State-of-the-Art Efficiency: Consistently achieves performance benchmarks that surpass many existing open-source and commercial video generation solutions.
• Consumer-Grade GPU Compatibility: Optimized to run efficiently on widely available hardware, making high-quality video generation accessible even on consumer-grade GPUs.
• Accelerated Inference: Powered by WaveSpeedAI’s cutting-edge optimization techniques, the model dramatically reduces latency and computational overhead, enabling rapid video synthesis without sacrificing output quality.

ComfyUI

wan-2.1/i2v-720p-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 Purpose Only: wan-2.1/i2v-720p-lora is exclusively designed for creative image-to-video conversion and is not intended for generating factually reliable content.
• Potential Inherent Biases: As a model built on data-driven techniques, it may reflect biases present in its training dataset.
• Input Sensitivity: The quality and consistency of the generated video is largely dependent on the clarity and detail of the input image, which may lead to variability in the output.
• Task-Specific Functionality: This model supports only image-to-video generation and does not extend to other video generative tasks such as text-to-video or video editing.

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/i2v-720p-lora" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "image": "https://d2g64w682n9w0w.cloudfront.net/media/dd703f8dc97646268d372cdd689fdccc/images/1747376115166619494_BvXVTPNJ.png",
    "prompt": "The video begins with a woman. A hydraulic press positioned above slowly descends towards the woman. Upon contact, the hydraulic press c5us4 crushes it, deforming and flattening the woman, causing the woman to collapse inward until the woman is no longer recognizable, crush on the ground",
    "negative_prompt": "",
    "loras": [
        {
            "path": "Remade-AI/Squish",
            "scale": 1
        }
    ],
    "size": "1280*720",
    "num_inference_steps": 30,
    "duration": 5,
    "guidance_scale": 5,
    "flow_shift": 5,
    "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