Qubico
  1. WanX
Qubico
  • Get Started
    • Overview
    • Quickstart
  • Endpoints
    • Flux
      • Flux with LoRA and Controlnet
      • Available LoRA and Controlnet
      • Flux API with Redux Variation, Fill, Inpaint and Outpaint
      • Create Task
        • Kontext
        • Text to Image
        • Image to Image
      • Get task
    • AI Hug
      • Get Task
      • Create Task
    • Faceswap
      • Multi Faceswap
      • Image Faceswap
      • Video Faceswap
      • Get Task
    • TTS
      • Zeroshot Text-to-Speech F5-TTS
      • Get Task
    • Trellis
      • Create Task
      • Get Task
    • WanX
      • Generate WanX Task with LoRA Using Qubico
      • Available LoRA Types for Wanx
      • Use Cases for Wanx LoRA
      • Use Cases for Wanx Control Camera
      • Create Task
        POST
      • Get Task
        GET
    • Skyreels
      • Create Task
      • Get Task
    • Framepack
      • Create Task
      • Get Task
    • Hunyuan Video
      • How to Make a Hunyuan API Call
      • Get Task
      • Generate Video
    • Mmaudio
      • Get Task
      • Generate Audio
    • DiffRhythm
      • Generate Audio
      • Get Task
    • Ace Step
      • Create Task
        • Text to Audio
        • Audio to Audio
        • Audio Edit
        • Audio Extend
      • Get Task
    • Tools
      • File Upload API
      • Video Upscale
      • Video Upscale-Get Task
      • Remove Background API
      • Remove Background-Get Task
      • Segment With Prompt API
      • Segment With Prompt API-Get Task
      • Image Upscale(Super Resolution) API
      • Image Upscale-Get Task
    • Account Management
      • Account Info
      • Task List Info
      • User Task History
  • Resources
    • Change Log
    • Output Storage
    • Unified API Schema
    • Webhook
    • Billings
  1. WanX

Create Task

POST
/api/v1/task

Overview#

The Qubico WanX API offers multiple advanced video generation models that can create high-quality videos from text prompts or images. All generated videos have a resolution of 480p and 85 frames.
WanX models are less censored than other alternatives and support NSFW content.

Models and Pricing#

ModelTask TypeDescriptionPrice
Qubico/Wanx txt2video-1.3bText-to-VideoLightweight text-to-video generation model$0.12 per generation
Qubico/Wanx txt2video-14bText-to-VideoAdvanced text-to-video generation model$0.28 per generation
Qubico/Wanx txt2video-14b-loraText-to-Video with LoRAGenerate video based on specific LoRA type and text prompt$0.28 per generation
Qubico/Wanx img2video-14bImage-to-VideoImage-to-video transformation model$0.28 per generation
Qubico/Wanx img2video-14b-loraImage-to-Video with LoRAGenerate video based on specific LoRA type and image$0.28 per generation
Qubico/Wanx img2video-14b-keyframeImage-to-Video KeyframeGenerate video from first and last frames$0.28 per generation
Qubico/Wanx img2video-14b-control-cameraImage-to-Video Control CameraGenerate video with camera motion control$0.28 per generation

Special Considerations#

1.
Prompt Quality: The quality of the prompt directly affects the quality of the generated video. Detailed, specific descriptions are recommended.
2.
Video Specifications: All generated videos are 85 frames, 30 inference steps, at 480p resolution.
3.
Processing Time: Video generation requires processing time. Webhook configuration is recommended to receive task completion notifications.
4.
Image Format: For the img2video-14b model, supported image formats include URL links or base64 encoded image data.
5.
Aspect Ratio: Two aspect ratios are supported: 16:9 (default) and 9:16.
6.
Motion Type: For the img2video-14b-control-camera model, this parameter determines how the camera moves in the generated video. Only one camera motion type is supported per generation, with static as the default.
7.
Motion Speed: For the img2video-14b-control-camera model, this sets how fast the camera moves, with 0.2 as the default value.
Request Request Example
Shell
JavaScript
Java
Swift
cURL
curl --location --request POST '/api/v1/task' \
--header 'x-api-key;' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "Qubico/wanx",
    "task_type": "txt2video-14b-lora",
    "input": {
        "prompt": "A girl with a playful smile leans forward on the ferry railing, holding onto her sunhat as the wind threatens to carry it away. She looks directly at the camera with bright, excited eyes, her laughter almost visible in her expression. The sun reflects off the sparkling water, and behind her, the coastline of a charming island town approaches. The camera slowly zooms out, capturing the anticipation of arrival.",
        "negative_prompt": "Overexposure, static, blurred details, subtitles, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, mutilated, redundant fingers, poorly painted hands, poorly painted faces, deformed, disfigured, deformed limbs, fused fingers, three legs",
        "lora_settings": [
            {
                "lora_type": "ghibli"
            }
        ]
    }
}'
Response Response Example
200 - Example 1
{
    "task_id": "string",
    "status": "pending",
    "created_at": "2019-08-24T14:15:22Z"
}

Request

Header Params

Body Params application/json

Examples

Responses

🟢200OK
application/json
Task created successfully
Body

🟠400Bad Request
🟠401Unauthorized
🔴500Server Error
Modified at 2025-07-06 07:00:28
Previous
Use Cases for Wanx Control Camera
Next
Get Task
Built with