Wan 2.2 I2V A14B Image-to-Video on Modular

Wan 2.2 I2V A14B is an image-to-video diffusion model from Wan AI. It animates a source image with prompt guidance and supports 480P and 720P video generation using the Wan A14B MoE architecture.

Deploy dedicated endpoint

Try in Playground

Example Usage

Input

Python


  import base64
  from openai import OpenAI
  
  client = OpenAI(
      base_url="https://model.api.modular.com",
      api_key="<your_api_token>",
  )
  
  response = client.responses.create(
      model="Wan-AI/Wan2.2-I2V-A14B-Diffusers",
      input="A campfire crackles in a forest clearing at night, sparks spiraling upward into a star-filled sky",
      extra_body={
          "provider_options": {
              "video": {
                  "height": 512,
                  "width": 512,
                  "steps": 28,
                  "num_frames": 81,
                  "frames_per_second": 16,
                  "response_format": "b64_json",
              }
          }
      },
  )
  
  video_data = response.output[0].content[0].video_data
  
  with open("output.mp4", "wb") as f:
      f.write(base64.b64decode(video_data))

Get your API token

Model Details

Developed by
Wan AI
Model family
Wan-AI/Wan2.2-I2V-A14B-Diffusers
Modality
Video,
Total Params
27B
Precision
BF16
Deployment options
Shared, Dedicated, Self-hosted

Why choose Wan 2.2 I2V A14B on Modular?

High performance, out of the box
Run leading open models with strong default performance and the ability to optimize down to the kernel — extracting more from every GPU.
Lower Infrastructure Costs
Deploy efficiently across NVIDIA and AMD hardware to reduce GPU count, increase throughput, and avoid expensive closed-model licensing.
Easy Integration
Integrate through an OpenAI-compatible endpoint, swap models freely, and scale across clouds or hardware without redesigning your application stack.

Want to self-host this model with our open source infrastructure?

Read How

🔥 Trending models

DeepSeek V4 Pro

DeepSeek V4 Pro is a 1.6T MoE model with 49B active parameters and a 1M context window, featuring hybrid attention for efficient long-context inference.

LLM

FLUX.2 Klein 9B

FLUX.2 [klein] 9B is a 9 billion parameter rectified flow transformer capable of generating images from text descriptions and supports multi-reference editing capabilities.

Image

GLM-5.1

GLM-5.1 by Zhipu AI is a 744B MoE model with 40B active parameters, optimized for long-horizon agentic engineering tasks.

LLM

Kimi K2.6

Kimi K2.6 by Moonshot AI is a ~1T MoE model with 32B active parameters, supporting text, image, and video input with reasoning and agentic capabilities.

LLM

Vision

Similar models

Wan 2.2 TI2V 5B

Wan 2.2 TI2V 5B is a compact text-and-image-to-video diffusion model from Wan AI. It supports both text-to-video and image-to-video generation at 720P and 24fps with a high-compression Wan 2.2 VAE.

Video

Wan 2.2 T2V A14B

Wan 2.2 T2V A14B is a text-to-video diffusion model from Wan AI. It uses a Mixture-of-Experts architecture with 14B active parameters per denoising step to generate 5-second videos from text prompts at 480P or 720P.