We use essential cookies to make our site work. With your consent, we may also use non-essential cookies to improve user experience and analyze website traffic…

DeepInfra raises $107M Series B to scale the inference cloud — read the announcement

Automatic Speech Recognition Embeddings Reranker Text Generation Text To Image Text To Music Text To Speech Text To Video World Model Zero Shot Image Classification

Docs

Pricing

Wan-AI/

Wan2.6-I2V

Partner

$0.10 / second

Turn any image into a video. Intelligent shot scheduling supports multi-shot storytelling, generating multi-shot narrative videos with consistent subjects, scenes, and atmosphere

Public

👁 Wan-AI/Wan2.6-I2V cover image

api versions

Input

Prompt

Text prompt describing the video content. (Default: empty)

Img Url

First-frame image: either a URL or base64-encoded image data

You need to log in to use this model

Settings

Negative Prompt

Negative prompt describing content to exclude. (Default: empty)

Audio Url

URL of audio file for synchronized audio and video. (Default: empty)

Resolution

Resolution tier of the generated video (720P or 1080P)

Duration

Duration of the generated video in seconds (2-15) (Default: empty, 2 ≤ duration ≤ 15)

Prompt Extend

Whether to enable prompt rewriting for better quality

Shot Type

Shot type: single continuous shot or multi switching shots

Watermark

Whether to add AI Generated watermark

Seed

Random seed for reproducibility (Default: empty, 0 ≤ seed ≤ 2147483647)

Output

Model Information

Wan2.6 image to video, Intelligent shot scheduling supports multi-shot storytelling, generating multi-shot narrative videos with consistent subjects, scenes, and atmosphere, with a maximum duration of 15 seconds. It delivers better instruction following, and improved visual fidelity.

👁 Footer Logo

👁 SOC 2 Certified
👁 ISO 27001 Certified

Have questions or need a custom solution?

Company