Model icon
wan2.5-image-to-video
Text to Video
Image to Video
Model:
Wan 2.5 API supports text-to-video and image-to-video for creative production, ads, product demos, and automated video pipelines.
Input
84/1500
Added 1/1

Drop files here, paste files, or add a URL. image/jpeg,image/png,image/webp · 10 MiB

Image Urls 1
——
Output

Example Output

This is sample data. Generate a new result to see real output.

Task ID:poyo-exampleCreated:Poyo official example
Status:finishedProgress:-
Examples
Pricing details

Transparent pricing with no hidden fees. Pay as you go.

Alibabawan2.5-image-to-video
480p or 832x480 - 5s
PoYo price
$0.150/video
30 credits
Official price
$0.250/video
Fal
You save
40%
Alibabawan2.5-image-to-video
720p or 1280x720 - 5s
PoYo price
$0.300/video
60 credits
Official price
$0.500/video
Fal
You save
40%
Alibabawan2.5-image-to-video
1080p or 1920x1080 - 5s
PoYo price
$0.450/video
90 credits
Official price
$0.750/video
Fal
You save
40%

* Actual fees are based on the final output.

Introduction

Complete guide to using Wan 2.5 API for Higher-Fidelity Video and Audio Generation

Wan 2.5 API for Higher-Fidelity Video and Audio Generation

Wan 2.5 on PoYo gives developers a cleaner step up from fast drafting models, with 5-second and 10-second outputs, text-to-video and image-to-video workflows, and support for synchronized background audio in the model family.

Key Features of Wan 2.5 API

The three most useful reasons to choose Wan 2.5 over faster draft-oriented video models.

01

Text-to-video and image-to-video in one family

Wan 2.5 gives developers both prompt-driven generation and image-led generation in the same model family, which keeps integration simpler when teams need both modes.

  • wan2.5-text-to-video for prompt-led generation
  • wan2.5-image-to-video for image-led workflows
  • One family for both ideation and guided creation

02

Synchronized audio and higher-resolution image-led generation

The official Wan 2.5 positioning highlights one-pass A/V sync, background audio support, and 480p, 720p, and 1080p image-led output, making it a practical step up when teams need better visual fidelity and richer output.

  • Background audio support in the model family
  • 480p, 720p, and 1080p output tiers
  • Useful for hero frames, explainers, and product-led motion
Wan 2.5 image-to-video source example

03

5s and 10s output with more size options

Wan 2.5 supports 5-second and 10-second generation with clearer tiering across size and resolution, which helps teams plan clip length, framing, and spend more predictably.

  • 5s and 10s output supported
  • Text mode uses exact size presets
  • Image mode uses resolution-based output tiers

What Can You Build With the Wan 2.5 API

01

Commercial concept clips

Generate polished short ad scenes, product mood films, and launch visuals.

02

Branded short-form video

Create social-ready clips with stronger visual fidelity than lightweight draft models.

03

Image-led motion generation

Turn static hero frames into animated shots without changing to a separate workflow.

04

API-native production pipelines

Fold Wan 2.5 into existing async job systems with controllable cost tiers.

How to Use Wan 2.5 API on PoYo

Step 1: Create your PoYo API key
Prepare a normal async PoYo video request with submit and status polling.
Create API Key →

Step 2: Choose the public model
Use wan2.5-text-to-video for prompt-based generation or wan2.5-image-to-video when you want to supply a starting image.
Add Credits →

Step 3: Pick duration and size tier
Select 5 seconds or 10 seconds, then choose the matching text size preset or image resolution before you submit.
View API Doc →

Wan 2.5 API Pricing on PoYo

Text-to-video: 832×480 starts at 30 credits for 5 seconds, 1280×720 starts at 60 credits, and 1920×1080 starts at 90 credits.

Image-to-video: 480p starts at 30 credits for 5 seconds, 720p starts at 60 credits, and 1080p starts at 90 credits.

Both workflows support 10-second output at double the 5-second tier.

Frequently Asked Questions about Wan 2.5 API

Which Wan 2.5 models are available on PoYo?

PoYo currently exposes wan2.5-text-to-video and wan2.5-image-to-video.

Does Wan 2.5 support 10-second output?

Yes. Both the text-to-video and image-to-video integrations on PoYo support 5-second and 10-second generation.

What is the difference between text and image mode parameters?

The text model uses exact size presets through the aspect_ratio field, while the image model uses a single image_urls entry and a resolution field.

Does Wan 2.5 support audio?

Yes. The Wan 2.5 model family is positioned around synchronized background audio and one-pass A/V sync, and PoYo exposes the audio setting in the current public workflow.

Why Choose PoYo for Wan 2.5 API Integration

01

One page for both workflows

Use text-to-video and image-to-video from the same product surface and async API style.

02

Clear parameter mapping

PoYo keeps the public request fields stable while the backend handles provider-specific mapping.

03

Transparent tiered pricing

Credits scale by duration and size so production teams can budget clips up front.

04

Production-ready delivery

Webhook support and task tracking make Wan 2.5 easier to run in real apps and internal tooling.