Does Wan Image-to-Video support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Wan Image-to-Video is available on request via Opper Enterprise — contact hello@opper.ai.

Where is Wan Image-to-Video hosted?

Wan Image-to-Video runs on US hosting routes through the Opper gateway.

Is Wan Image-to-Video trained on prompts and outputs?

No. Every hosting route for Wan Image-to-Video is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Wan Image-to-Video?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Wan Image-to-Video. Contact hello@opper.ai to receive it.

Wan Image-to-Video

by Pruna

Wan-i2v is Pruna's optimized image-to-video model that turns static images into animated video using natural language motion descriptions. Unlike pure text-to-video, it anchors generation to an input image while letting you direct motion and scene changes through text prompts. The model supports 480p and 720p output (832x480 or 1280x720 pixels) at a 16:9 aspect ratio, with configurable frame counts from 81 to 121 and frame rates from 5 to 30 fps, where 81 frames give the best results. Optional frame interpolation produces smoother 30 fps output, and advanced controls include sample shifting, custom LoRA weights, and seed control for reproducibility. Wan-i2v is a good fit for bringing existing images to life within controlled parameters, from product showcases and marketing content to character animation and visual effects. It bridges static image creation and full video generation, making it valuable where the visual starting point is known and motion needs to be added.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

—

Max output

—

Input price

— /1M

Output price

— /1M

US residency available
Zero data retention via Enterprise
No training by default
GDPR DPA available

Available routes

Wan Image-to-Video runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output
Pruna	US	Enterprise	No	—	—

Training posture across routes: No training on prompts by default.

Data handling per route

Each route hosting Wan Image-to-Video has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Pruna — United States🇺🇸

Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.

Zero data retention: Available via Opper Enterprise contract.
Training: No training on customer data.
Logging: Abuse monitoring
Third-party access: None disclosed
GDPR DPA: DPA available
Transfer mechanism: SCCs

Get started

Call Wan Image-to-Video through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into your coding agent — Claude Code, Cursor, Codex, and more — and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "pruna/wan-i2v",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);