Skip to main content

Deploy Wan 2.2

Video

Wan 2.2 is Alibaba Tongyi Lab's latest video generation family. The 5B variants use MoE architecture for efficient generation on consumer GPUs, while 14B variants deliver higher quality at HD resolution on A100 GPUs.

Deploy Wan 2.2 in minutes

Starting at $0.66/hr on dedicated GPU

Available Variants (4)

ModelGPUVRAMPriceAction
Wan 2.2 5B Text-to-Video
5B Text-to-Video
RTX A600048 GB$0.66/hrDeploy
Wan 2.2 5B Image-to-Video
5B Image-to-Video
RTX A600048 GB$0.66/hrDeploy
Wan 2.2 14B Text-to-Video
14B Text-to-Video
A100 80GB PCIe80 GB$1.85/hrDeploy
Wan 2.2 14B Image-to-Video
14B Image-to-Video
A100 80GB PCIe80 GB$1.85/hrDeploy

Prices include 30% service fee. Billed per minute while running.

Requirements

Wan 2.2 requires 48–80GB VRAM depending on variant. Consumer GPUs like the RTX 5080 (16GB) or RTX 4090 (24GB) cannot run this model.

On ModelPilot, deploy on a dedicated cloud GPU (up to 80GB VRAM) starting at $0.66/hr with no setup required.

Includes ComfyUI with video-optimized workflows. Video models require more GPU memory for frame buffers.

Use Cases

  • Text-to-video generation
  • Image-to-video animation
  • Social media content creation
  • Product demo videos

Related Models

Frequently Asked Questions

How much VRAM does Wan 2.2 need?

Wan 2.2 requires 48–80GB VRAM depending on the variant.

How much does it cost to run Wan 2.2?

Starting at $0.66/hr on a dedicated GPU. Billed per minute while running, with auto-stop when credits run out.

How long does Wan 2.2 take to deploy?

Video models typically take 15–30 minutes for first deployment (model download + setup). Subsequent starts are faster.

Can I run Wan 2.2 on my local GPU?

Wan 2.2 requires 48GB+ VRAM, which exceeds most consumer GPUs. Cloud GPUs (A6000 48GB, A100 80GB) are recommended.

Ready to deploy Wan 2.2?

Pick your GPU and have it running in minutes. No infrastructure setup required.