SandBase is live — $1 in free credits on signupStart free ›

Alibaba modelsvideo generation api

alibaba/wan/2.2/vace-fun/inpainting

Wan 2.2 Vace Fun is Alibaba's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.

Input
The text prompt to guide video generation.
The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL to the guiding mask file. If provided, the model will use this mask as a reference to create masked video using salient mask tracking. Will be ignored if mask_video_url is provided.
URL to the source video file. Required for inpainting.
Resolution of the generated video. Allowed values: auto, 240p, 360p, 480p, 720p.
Random seed for reproducibility. If None, a random seed is chosen.
Idle

Example output — click Run to generate your own

API README

Wan 2.2 VACE Fun Inpainting

Wan 2.2 VACE Fun Inpainting is the Wan 2.2 workflow for masked video reconstruction. It models visual appearance and time together so the route’s written direction, source imagery, speech, masks, or structural conditions influence one coherent result rather than a collection of disconnected frames or a generic endpoint response.

Choose this exact route when the available assets and deliverable specifically call for masked video reconstruction. Identify every subject and source, state the desired action or transformation, then describe camera behavior, pacing, environment, lighting, atmosphere, and preservation requirements; local schema fields handle resolution, duration, seed, and delivery separately from the creative brief.

Highlights

  • 2.2 Temporal inpainting. Regenerates masked video areas coherently across time.
  • 2.2 Motion-aware edge blending. Matches movement, texture, perspective, and lighting at edit boundaries.
  • 2.2 Prompt-directed replacement. Introduces requested content inside the selected region.
  • 2.2 Unmasked-region stability. Preserves source content outside the reconstruction area.

Pricing

ResolutionPrice per generated second
Auto$0.050
240p$0.050
360p$0.050
480p$0.050
720p$0.100

When to Use

✅ Good fit❌ Consider alternatives
The project needs this exact video inpainting workflowThe intended task belongs to a different media route
Available source media matches every required fieldRequired assets or usage rights are unavailable
The brief can define subject, action, camera, and styleOutput must be deterministic at frame or pixel level
Supported duration, resolution, and framing fit deliveryFinal placement requires unsupported specifications
An asynchronous generation job fits productionA live or frame-synchronous response is mandatory

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",
  "mask": "example",
  "seed": 1,
  "video": "https://example.com/source.mp4"
}

Technical Specs

SpecValue
Model IDalibaba/wan/2.2/vace-fun/inpainting
Input fieldsmask (string)<br>seed (integer)<br>video (string)<br>prompt (string)<br>resolution (string; auto, 240p, 360p, 480p, 720p)<br>aspect_ratio (string; 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16)
Required inputprompt
Output fieldsurl, content_type
ExecutionAsynchronous job

Related Models

Related Models

alibaba/wan/2.2/vace-fun/depthWan 2.2 Vace Fun by Alibaba - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions.alibaba/wan/2.2/vace-fun/outpaintingWan 2.2 Vace Fun by Alibaba - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions.alibaba/wan/2.2/vace-fun/reframeWan 2.2 Vace Fun by Alibaba - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions.alibaba/wan/2.2/animate/moveWan 2.2 Animate by Alibaba - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions.alibaba/wan/2.2/animate/replaceWan 2.2 Animate is Alibaba's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.alibaba/wan/2.2/fun-controlWan 2.2 Fun Control is Alibaba's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.alibaba/wan/2.2/i2v-480p-loraWan 2.2 image-to-video LoRA generation with fixed 480p output.alibaba/wan/2.2/i2v-720p-loraWan 2.2 image-to-video LoRA generation with fixed 720p output.