> ## Documentation Index
> Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
> Use this file to discover all available pages before exploring further.

# WanCameraImageToVideo - ComfyUI Built-in Node Documentation

> The WanCameraImageToVideo node prepares conditioning and latent data for camera-controlled video generation from images.

The WanCameraImageToVideo node prepares conditioning and latent data for camera-controlled video generation from images. It takes positive and negative conditioning prompts, along with optional inputs such as a starting image, CLIP vision output, and camera conditions, and outputs updated conditioning plus an empty latent tensor ready for a video model to fill in.

## Inputs

| Parameter | Description | Data Type | Required | Range |
| - | - | - | - | - |
| `positive` | Positive conditioning prompts for video generation | CONDITIONING | Yes | - |
| `negative` | Negative conditioning prompts to avoid in video generation | CONDITIONING | Yes | - |
| `vae` | VAE model for encoding images to latent space | VAE | Yes | - |
| `width` | Output video width in pixels (default: 832, step: 16) | INT | Yes | 16 to MAX\_RESOLUTION |
| `height` | Output video height in pixels (default: 480, step: 16) | INT | Yes | 16 to MAX\_RESOLUTION |
| `length` | Number of frames in the video sequence (default: 81, step: 4) | INT | Yes | 1 to MAX\_RESOLUTION |
| `batch_size` | Number of videos to generate simultaneously (default: 1) | INT | Yes | 1 to 4096 |
| `clip_vision_output` | Optional CLIP vision output for additional conditioning | CLIP\_VISION\_OUTPUT | No | - |
| `start_image` | Optional starting image to initialize the video sequence. When provided, only the first `length` frames are used, and the image is resized to match the specified `width` and `height`. The first frames of the sequence are encoded into the latent and a mask is applied to blend the starting frames with generated content. | IMAGE | No | - |
| `camera_conditions` | Optional camera embedding conditions for video generation. When provided, these conditions are applied to both the positive and negative conditioning. | WAN\_CAMERA\_EMBEDDING | No | - |

**Note:** When `start_image` is provided, the node sets `concat_latent_image` and `concat_mask` values on both `positive` and `negative` conditioning. The `camera_conditions` and `clip_vision_output` parameters are optional, but when provided, they modify the conditioning for both the positive and negative prompts.

## Outputs

| Output Name | Description | Data Type |
| - | - | - |
| `positive` | Modified positive conditioning with applied camera conditions, clip vision output, and/or starting image data | CONDITIONING |
| `negative` | Modified negative conditioning with applied camera conditions, clip vision output, and/or starting image data | CONDITIONING |
| `latent` | Empty video latent representation for use with video models. The latent tensor has dimensions \[batch\_size, 16, frames, height/8, width/8], where frames is calculated as ((length - 1) // 4) + 1. | LATENT |

> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanCameraImageToVideo/en.md)

***

**Source fingerprint (SHA-256):** `467a82be0dfd6ac1c3b2dd2a6cb02e0d0749de4536a7fbdb000456b817b20ebb`