WaveSpeedAI APIWan I2V 720p LoRA

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

ParameterTypeRequiredDefaultRangeDescription
imagestringYeshttps://d2g64w682n9w0w.cloudfront.net/media/dd703f8dc97646268d372cdd689fdccc/images/1747376115166619494_BvXVTPNJ.png-The image for generating the output.
promptstringYesThe 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-The prompt for generating the output.
negative_promptstringNo--The negative prompt for generating the output.
lorasarrayNo[]max 3 itemsThe LoRA weights for generating the output.
loras[].pathstringYes-Path to the LoRA model
loras[].scalefloatYes-0.0 ~ 4.0Scale of the LoRA model
sizestringNo1280*7201280*720, 720*1280The size of the output.
num_inference_stepsintegerNo301 ~ 40The number of inference steps.
durationintegerNo55 ~ 10Generate video duration length seconds.
guidance_scalenumberNo51.01 ~ 10.00The guidance scale for generation.
flow_shiftnumberNo51.0 ~ 10.0The shift value for the timestep schedule for flow matching.
seedintegerNo-1-1 ~ 9999999999The seed for random number generation.
enable_safety_checkerbooleanNotrue-Whether to enable the safety checker.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Query Parameters

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2025 WaveSpeedAI. All rights reserved.