Header Logo

Docs

Start

Header Logo

Start

Header Logo

Docs

Start

All Models

WaveSpeed logo

WAN 2.1 Mocha

WAN 2.1 Mocha replaces the main character in footage using a reference image, retaining the source performance’s movement and expressions within the scene.

Video editing

Based on verified input duration.

OfferingPrice (USD)
Resolution: 480p$0.04 / input second
Resolution: 720p$0.08 / input second
  • Based on the video input; billing steps apply in this order:
  • Round input duration up to a whole second.
  • Cap billed duration at 120 seconds.
  • Bill at least 3 seconds.
  • Round the total charge up to the next $0.01.

WAN 2.1 Mocha

WAN 2.1 Mocha edits existing footage by replacing its main character with the character depicted in a reference image. The video provides the performance and setting, while the image defines the replacement’s identity and appearance. Optional text can guide the transformation.

The resulting video carries over the actor’s body movement and facial expressions, along with the original timing. Lighting and camera perspective remain connected to the source scene, and the replacement character’s appearance is maintained across frames.

What it's good for

Character designers can test a proposed identity against an existing performance. Seeing a design move through a scene helps teams assess its expression and screen presence in the context of established action.

Mocha also fits avatar-led videos and advertising concept work. A recorded performance becomes the basis for different character treatments, allowing creative reviews to focus on how each appearance works with the acting and shot design.

Model ID

wavespeed-ai/wan-2.1-mocha

Output Type

Video

Pricing

From $0.04 / input second

Provider

WaveSpeed

Hosting

Protoface

WAN 2.1 Mocha

WAN 2.1 Mocha edits existing footage by replacing its main character with the character depicted in a reference image. The video provides the performance and setting, while the image defines the replacement’s identity and appearance. Optional text can guide the transformation.

The resulting video carries over the actor’s body movement and facial expressions, along with the original timing. Lighting and camera perspective remain connected to the source scene, and the replacement character’s appearance is maintained across frames.

What it's good for

Character designers can test a proposed identity against an existing performance. Seeing a design move through a scene helps teams assess its expression and screen presence in the context of established action.

Mocha also fits avatar-led videos and advertising concept work. A recorded performance becomes the basis for different character treatments, allowing creative reviews to focus on how each appearance works with the acting and shot design.