---
title: "wan-i2v"
url: "https://docs.api.pruna.ai/apis/models-api-0/versions/7dfbc266-0f94-4c90-8518-d9e4d1a245ec/schemas/wan-i2v"
---

> Full API specification: https://docs.api.pruna.ai/apis/models-api-0/versions/7dfbc266-0f94-4c90-8518-d9e4d1a245ec.md

# wan-i2v

AI model based on wan image to video for video generation. Rate limit: 30 requests per minute.

## OpenAPI definition

```yaml
openapi: 3.0.3
info:
  title: P-API
  version: 0.3.0
servers:
  - url: https://api.pruna.ai
    description: Production server
components:
  schemas:
    wan-i2v:
      type: object
      required:
        - input
      properties:
        input:
          type: object
          properties:
            seed:
              title: Seed
              description: Random seed. Leave blank for random
              type: integer
            image:
              title: Image
              format: uri
              description: Input image to generate video from.
              type: string
            prompt:
              title: Prompt
              description: Prompt for video generation
              type: string
            go_fast:
              title: Go Fast
              default: true
              description: Enable speed optimizations for faster video generation.
              type: boolean
            last_image:
              title: Last Image
              format: uri
              description: Optional last image to condition the video generation. If provided,
                creates smoother transitions between frames.
              type: string
            num_frames:
              title: Num Frames
              default: 81
              maximum: 121
              minimum: 81
              description: Number of video frames. 81 frames give the best results
              type: integer
            resolution:
              enum:
                - 480p
                - 720p
              title: resolution
              description: Resolution of video. 16:9 corresponds to 832x480px, and 9:16 is
                480x832px
              default: 480p
              type: string
            sample_shift:
              title: Sample Shift
              default: 12
              maximum: 20
              minimum: 1
              description: Sample shift factor
              type: number
            frames_per_second:
              title: Frames Per Second
              default: 16
              maximum: 30
              minimum: 5
              description: Frames per second. Note that the pricing of this model is based on
                the video duration at 16 fps
              type: integer
            interpolate_output:
              title: Interpolate Output
              default: false
              description: Interpolate the generated video to 30 FPS using ffmpeg
              type: boolean
            disable_safety_checker:
              title: Disable Safety Checker
              default: false
              description: Disable safety checker for generated video.
              type: boolean
            lora_scale_transformer:
              title: Lora Scale Transformer
              default: 1
              description: Determines how strongly the transformer LoRA should be applied.
              type: number
            lora_scale_transformer_2:
              title: Lora Scale Transformer 2
              default: 1
              description: Determines how strongly the transformer_2 LoRA should be applied.
              type: number
            lora_weights_transformer:
              title: Lora Weights Transformer
              description: Load LoRA weights for the HIGH transformer. Supports arbitrary
                .safetensors URLs from the Internet (for example,
                'https://huggingface.co/TheRaf7/instagirl-v2/resolve/main/Instagirlv2.0_hinoise.safetensors')
              type: string
            lora_weights_transformer_2:
              title: Lora Weights Transformer 2
              description: Load LoRA weights for the LOW transformer_2. Supports arbitrary
                .safetensors URLs from the Internet. Can be different from
                transformer LoRA. (for example,
                'https://huggingface.co/TheRaf7/instagirl-v2/resolve/main/Instagirlv2.0_lownoise.safetensors')
              type: string
          required:
            - prompt
            - image
          additionalProperties: false
      description: "AI model based on wan image to video for video generation. Rate
        limit: 30 requests per minute."
```