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

Alibaba modelsvideo generation api

alibaba/wan/2.2/image-to-video/lora

Wan 2.2 Lora is Alibaba's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.

Input
The text prompt to guide video generation.

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

URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.

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

URL of the end image.
Resolution of the generated video (480p, 580p, or 720p). Allowed values: 480p, 720p.
LoRA weights to be used in the inference.
If true, the video will be reversed.
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.
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 Image to Video LoRA

Wan 2.2 Image to Video LoRA is the Wan 2.2 adapted workflow for image-anchored animation. 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 image-anchored animation. 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 LoRA Reference-frame animation. Uses the supplied still as the visual foundation for motion.
  • 2.2 LoRA Subject identity retention. Keeps important appearance cues recognizable as the scene develops.
  • 2.2 LoRA Natural temporal movement. Creates coherent subject and environmental dynamics across frames.
  • 2.2 LoRA Prompt-directed cinematography. Interprets action, camera movement, pacing, lighting, and atmosphere. The route adds a lightweight task adaptation.

Pricing

ResolutionBilling unitPrice
480pPer generated second$0.040
720pPer generated second$0.080

When to Use

✅ Good fit❌ Consider alternatives
The project needs this exact named workflowThe intended task belongs to another media route
All required reference or control media is availableNecessary assets or rights are unavailable
The brief can state transformation and preservation goalsOutput must be deterministic at pixel or frame level
Supported duration, resolution, and format fit deliveryFinal placement requires unsupported specifications
An asynchronous generated result fits productionA live frame-synchronous response is mandatory

Prompt Guide

Identify the primary subject and every source or condition, state the intended transformation or action, then describe composition, camera or viewpoint, lighting, materials, pacing, atmosphere, and exact preservation requirements. Refer to multiple inputs in their schema order.

{
  "prompt": "A precisely directed composition with explicit subject, transformation, camera or viewpoint, lighting, material, and preservation requirements",
  "image": "https://example.com/reference.png",
  "seed": 1,
  "loras": [],
  "end_image": "https://example.com/reference.png"
}

Technical Specs

SpecValue
Model IDalibaba/wan/2.2/image-to-video/lora
Input fieldsseed (integer)<br>image (string)<br>loras (array)<br>prompt (string)<br>end_image (string)<br>resolution (string; 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)<br>reverse_video (boolean)
Required inputprompt, image
Output fieldsurl, content_type
ExecutionAsynchronous job

Related Models

  • alibaba/wan/2.1/text-to-video
  • alibaba/wan/2.1/image-to-video
  • alibaba/wan/2.1/vace

Related Models