ModelsVideo modelsExplore Wan Video Models and Workflows
AI model directory

Explore Wan Video Models and Workflows

Understand the Wan model family, then review the image input and clip settings in WeShop AI’s Wan workspace. Keep the selected integration details with each output.

Understand the Wan model family, then review the image input and clip settings in WeShop AI’s Wan workspace. Keep the selected integration details with each output.

Choose by the Task You Need to Complete

Choose the workflow that matches your starting material and the result you need.

Sneaker first-frame reference
Source/reference image for this task.

Animate a prepared product image

Use the current Wan workspace when the source image already establishes the subject and composition. Describe a modest action or camera movement.

Potted plant reference input
Source/reference image for this task.

Understand the model family

Consult the official model documentation for named releases and input types. Keep those release names separate from the integration label shown in the workspace.

Coffee cup reference input
Source/reference image for this task.

Compare the same image-led brief

Use the same product image and a shared clip length in Wan and another image-to-video workspace. Inspect shape, texture, and movement in the actual clips.

Compare workflows

Compare Wan

Compare the available inputs and task fit. Check the selected workspace for current settings before generating.

Model / entryInput or referenceWhen to review itAction
Wan AI on WeShopImage reference and text promptOpen the current image-led video workspace; record its displayed model details.
Wan AI on WeShop
Input or reference
Image reference and text prompt
When to review it
Open the current image-led video workspace; record its displayed model details.

Example Briefs and Model Comparisons

Review real inputs and generated outputs alongside their complete prompts.

Sneaker first-frame reference
Reference input — not a generated video result.

A five-second product camera move.

Reference input for this example; the actual video output remains pending.

A slow camera slide reveals the sneaker from a slightly different angle. Keep the sole, laces, logo placement, and color panels consistent with the reference. The shoe stays still on the pedestal. Soft studio light.
Potted plant reference input
Reference input — not a generated video result.

A still-life image with controlled environmental motion.

Reference input for this example; the actual video output remains pending.

Keep the plant pot and window frame fixed. Let the leaves move gently in a light breeze while soft sunlight shifts subtly across the table. A steady camera with no scene change.
Coffee cup reference input
Reference input — not a generated video result.

The same cup image across two video workflows.

Reference input for this example; the actual video output remains pending.

Start from the reference cup on a wooden table. A faint wisp of steam rises while the camera slowly pushes in. Keep the cup handle, rim, and table edges consistent. Natural morning light.
Wan AI · 5s · actual WeShop AI output.

Wan AI video — example 1

Actual video generated on WeShop AI from the documented brief.

A slow camera slide reveals the sneaker from a slightly different angle. Keep the sole, laces, logo placement, and color panels consistent with the reference. The shoe stays still on the pedestal. Soft studio light.
Wan AI · 8s · actual WeShop AI output.

Wan AI video — example 2

Actual video generated on WeShop AI from the documented brief.

Keep the plant pot and window frame fixed. Let the leaves move gently in a light breeze while soft sunlight shifts subtly across the table. A steady camera with no scene change.
Wan AI · 5s · actual WeShop AI output.

Wan AI video — example 3

Actual video generated on WeShop AI from the documented brief.

Start from the reference cup on a wooden table. A faint wisp of steam rises while the camera slowly pushes in. Keep the cup handle, rim, and table edges consistent. Natural morning light.
Kling 3.0 · 5s · actual WeShop AI output.

Kling 3.0 video — example 3

Actual video generated on WeShop AI from the documented brief.

Start from the reference cup on a wooden table. A faint wisp of steam rises while the camera slowly pushes in. Keep the cup handle, rim, and table edges consistent. Natural morning light.

How to Start

Prepare your brief and source assets, check the current controls, then inspect the generated result.

Illustration of preparing a plant reference image
Editorial illustration; not a WeShop workspace screenshot.

Prepare an image

Choose a sharp source with a clear subject and suitable framing.

Illustration of describing subtle movement from a plant image
Editorial illustration; not a WeShop workspace screenshot.

Describe a short movement

Open Wan AI, attach the image, and set a duration from the available choices.

Illustration of reviewing generated plant video frames
Editorial illustration; not a WeShop workspace screenshot.

Review the clip

Check subject details and motion before saving the selected output.

Continue Your Creative Workflow

Open the relevant workspace or supporting workflow to continue your task.

FAQ

How do you choose the right AI model?

Direct answers about model inputs, workflows, settings, and availability.

Which Wan version does WeShop AI currently show?

The reviewed workspace is labeled Wan AI and does not display a numbered model version. Check the integration details when selecting a task; the official Wan repository describes named releases separately.

What input does the Wan workspace use?

The current workspace provides an image input and a text prompt. Start with a clear reference image and describe the movement or camera direction you want.

What clip durations are visible?

The current Wan workspace displays durations from 3 to 8 seconds. Check the selected value and point cost before generating a clip.

How can I compare Wan with another model?

Use the same reference, motion prompt, and a duration supported by both workspaces. Record the settings and compare subject shape, temporal consistency, and how well the movement follows the brief.