MODEL & WORKFLOW GUIDE · WAN

Wan 2.2 Online Generator

Compare Wan 2.2 T2V and I2V workflows: the standard video entry accepts text or a first frame, while Tintmill Plus V1.0 is image-to-video only. The separate Wan 2.2 Image entry creates a still image and does not produce a clip.

Open Wan 2.2

Sign in and review your credit balance and the task estimate before AI generation.

Editorial illustration for the Wan 2.2 workflow guide

Editorial stock photograph · not a model output

When to Choose Wan 2.2

Animating a chosen first frame at 480P or 720P for five or eight seconds, or preparing a still frame before the motion step.

Wan 2.2 Inputs, Sizes and Variants

These are the settings exposed by Tintmill's connected catalog. The available duration can depend on the selected size; the studio shows compatible combinations. A listed option is not a claim about open weights, a shared architecture or identical capabilities across variants.

OptionInput workflowOutput sizesClip durations
Wan 2.2Text to video / Image to video480P / 720P5 / 8 seconds
Tintmill Plus V1.0Image to video480P / 720P5 / 8 seconds
Wan 2.2 ImageText to image1KStill image

A Useful Wan 2.2 Prompt

For Wan 2.2 I2V, describe what should move after the uploaded frame rather than re-describing every visible object. Keep the camera direction separate.

Prepare your prompt

Wan 2.2 Example Prompts

Original editorial starting points. These prompts have not been submitted as model-quality tests.

01 · EDITORIAL PROMPT

From the uploaded harbor frame, let the moored boat rock gently and its reflection ripple; fixed camera, no new objects.

Use this prompt
02 · EDITORIAL PROMPT

A slow lateral camera move past a stone archway, distant leaves moving softly, one continuous five-second shot.

Use this prompt
03 · EDITORIAL PROMPT

A cinematic still of a lighthouse on a storm-dark coast, beam facing left, wide composition prepared for later animation.

Use this prompt

Version, Provider and Usage Rights

Origin and release

Wan-AI's official Wan2.2-I2V-A14B model card. Official release reference.

Architecture and workflow scope

The upstream A14B design uses two diffusion experts for higher-noise and lower-noise denoising stages. It is an image-to-video checkpoint; the separate still-image option in this guide is not that same video input contract.

License for the identified version

The official A14B upstream weights use Apache 2.0. The separate Tintmill Plus hosted route is not assigned that license solely from its family name.

Tintmill series names identify selected hosted models and output settings. They do not mean that Tintmill independently trained the underlying model. Review the applicable model license and service terms for your intended use. Content rights and the generation data policy explain the service relationship.

Wan 2.2 Questions

01Which Wan 2.2 options can I use here?+

This guide covers Wan 2.2, Tintmill Plus V1.0, Wan 2.2 Image. The comparison lists each option's supported inputs, sizes and durations. Availability and the credit quote are checked before submission.

02How is a Wan 2.2 request charged?+

Image tasks use image units and video tasks use a separate video-credit balance. The selected variant, output size, count and duration determine the total shown in the studio. See Pricing for purchase availability. Generation requires sufficient account credits.

03Are the Wan 2.2 examples actual generated outputs?+

The prompts are original editorial starting points, and the illustration is stock photography. Neither is a benchmark or a demonstration of this model's output. Your uploaded files and generated results remain private to your account.

Related Model Workflows

Compare all model families · Open the video generator

Prepare a Wan 2.2 request