Wan 2.2 VACE Fun Depth

Wan 2.2 VACE Fun Depth is a depth-guided video control route in Alibaba’s Wan family. It uses depth structure to guide geometry and movement, combining prompt understanding with the visual and temporal modeling needed to keep subjects, scenes, and requested changes coherent across the result.

The 2.2 configuration is designed for a specific production path rather than a generic media request. Build the brief around subject, action or transformation, environment, camera language, lighting, pacing, sound where supported, and exact preservation requirements; then use the local duration, resolution, framing, and seed controls for delivery.

Highlights

• Coherent visual generation. Coordinates subjects, environment, composition, and requested action instead of rendering prompt elements independently.
• Temporal continuity. Maintains scene logic and movement across frames for a usable moving sequence.
• Prompt-led direction. Uses written direction to define subject, action, camera, style, atmosphere, and delivery intent.
• VACE task control. Applies a dedicated structural, mask, canvas, or framing condition through the VACE workflow.

Pricing

When to Use

Prompt Guide

Describe the result as a shot or design brief: identify subjects and references, state the action or transformation, specify environment and composition, then add camera behavior, lighting, pacing, style, sound, and preservation constraints where relevant. Use exact reference identifiers exposed by the local schema.

{
  "prompt": "A cinematic scene with clearly directed subject action, camera movement, lighting, pacing, and atmosphere",
  "seed": 1,
  "video": "https://example.com/source.mp4",
  "resolution": "auto"
}

Technical Specs

Related Models

• alibaba/wan/2.2/vace-fun/inpainting — Compare this concrete local family route.
• alibaba/wan/2.2/vace-fun/outpainting — Compare this concrete local family route.
• alibaba/wan/2.2/vace-fun/reframe — Compare this concrete local family route.