minimaxiH3 Get access
QwenImage-to-videoVendor content policy applies

Wan-2.5 Image-to-video

Bring static images to life with dynamic motion, lighting consistency, and synchronized audio. This variant smoothly animates reference visuals into short video sequences.

$0.053per secondStarting price at the base resolution and quality tier.
$0.42Typical 8-second clip at the base tier. Longer or higher-resolution outputs scale with duration and tier.
Pay per useBilled per request from your balance. No subscription, no minimum.
Sample output · prompt: “A cute magical girl with pink twin-tails is undergoing a brilliant transformation sequence. She is surrounded by shimmering starlight and floating ribbons as her clothes magically dissolve into a detailed battle dress. A…”

What it does

Wan-2.5 Image-to-video, in practice.

Wan 2.5 is a state-of-the-art, open-source video foundation model developed by Alibaba's Wan AI team. It is designed to generate high-quality, cinematic videos complete with synchronized audio directly from text or image prompts. The model represents a significant advancement in the field of generative AI, aiming to lower the barrier for creative video production. Its core contribution lies in its ability to produce coherent, dynamic, and narratively consistent video clips with a high degree of realism and integrated audio-visual elements, such as lip-sync and sound effects, in a single, streamlined process.

  • Unified Audio-Visual Synthesis: Unlike many models that require separate steps for video and audio generation, Wan 2.5 creates video with natively synchronized audio, including voice, sound effects, and lip-sync, in one step.
  • High-Fidelity, High-Resolution Output: The model is capable of generating videos in multiple resolutions, including 480p, 720p, and full 1080p HD, with significant improvements in visual quality and frame-to-frame stability over its predecessors.
  • Extended Video Duration: Wan 2.5 can generate video clips up to 10 seconds in length, offering more creative flexibility for storytelling compared to other models in its class.
  • Advanced Cinematic Control: The model demonstrates a sophisticated understanding of cinematic language, allowing for precise control over camera movement, shot composition, and character consistency within scenes.
  • Open-Source Commitment: Following the precedent set by earlier versions, the Wan series of models, including Wan 2.5, are open-sourced to encourage research, development, and innovation within the broader AI community.
  • Content Creation: Generating short-form videos for social media, marketing campaigns, and digital advertising.

Run Wan-2.5 Image-to-video

from $0.053/sec
Drop an image hereor click to choose a fileFiles stay in your project. Nothing is trained on.
duration
resolution
Invite code opens Chat with this model loaded. No code yet? Join the waitlist — we count which models people ask for.

Parameters

What you can set.

ParameterWhat it doesOptions
audioAudio URL to guide generation (optional).
durationThe duration of the generated media in seconds.5 10
enable_prompt_expansionIf set to true, the prompt optimizer will be enabled.default
imageThe image for generating the output.
negative_promptNegative prompt for the generation.
promptThe prompt for generating the output.
resolutionThe resolution of the generated video.480p 720p 1080p
generate_audioWhether to automatically add audio to the generated video.default True
seedThe random seed to use for the generation. -1 means a random seed will be used.default -1

Sample prompt

The prompt behind the sample.

A cute magical girl with pink twin-tails is undergoing a brilliant transformation sequence. She is surrounded by shimmering starlight and floating ribbons as her clothes magically dissolve into a detailed battle dress. A close-up shot focuses on her determined, large blue eyes. The background is a fantastical starry sky. Japanese anime style, vibrant colors, magical particle effects, dynamic motion, a mix of Studio Ghibli and Makoto Shinkai art styles.
seed: 579955138duration: 5resolution: 720penable_prompt_expansion:

FAQ

Short answers.

How much does Wan-2.5 Image-to-video cost?

Pricing starts at $0.053 per second of video at the base resolution; higher resolutions and longer durations cost more. An 8-second clip at the base tier is about $0.42. Usage is billed per request from your balance — no subscription.

Does Wan-2.5 Image-to-video run uncensored here?

No. Qwen applies its own content policy to this model regardless of where it is called from. For a route without an extra platform filter use Uncensored MiniMax H3; this page lists Wan-2.5 Image-to-video for everything else it does well.

What does Wan-2.5 Image-to-video take as input?

It is a image-to-video model. Bring static images to life with dynamic motion, lighting consistency, and synchronized audio. This variant smoothly animates reference visuals into short video sequences.

How do I use it?

Enter an invite code to open Chat with the model loaded, or join the waitlist. We open seats in batches and track which models are requested most.

Related

Models people compare with this one.

Run Wan-2.5 Image-to-video.

Invite code opens Chat with the model loaded. No code — join the waitlist and we will count the request.

Get access Browse models