Skip to main content
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The WanCameraImageToVideo node converts images to video sequences by generating latent representations for video generation. It processes conditioning inputs and optional starting images to create video latents that can be used with video models. The node supports camera conditions and clip vision outputs for enhanced video generation control.

Inputs

ParameterData TypeRequiredRangeDescription
positiveCONDITIONINGYes-Positive conditioning prompts for video generation
negativeCONDITIONINGYes-Negative conditioning prompts to avoid in video generation
vaeVAEYes-VAE model for encoding images to latent space
widthINTYes16 to MAX_RESOLUTIONOutput video width in pixels (default: 832, step: 16)
heightINTYes16 to MAX_RESOLUTIONOutput video height in pixels (default: 480, step: 16)
lengthINTYes1 to MAX_RESOLUTIONNumber of frames in the video sequence (default: 81, step: 4)
batch_sizeINTYes1 to 4096Number of videos to generate simultaneously (default: 1)
clip_vision_outputCLIP_VISION_OUTPUTNo-Optional CLIP vision output for additional conditioning
start_imageIMAGENo-Optional starting image to initialize the video sequence
camera_conditionsWAN_CAMERA_EMBEDDINGNo-Optional camera embedding conditions for video generation
Note: When start_image is provided, the node uses it to initialize the video sequence and applies masking to blend the starting frames with generated content. The camera_conditions and clip_vision_output parameters are optional but when provided, they modify the conditioning for both positive and negative prompts.

Outputs

Output NameData TypeDescription
positiveCONDITIONINGModified positive conditioning with applied camera conditions and clip vision outputs
negativeCONDITIONINGModified negative conditioning with applied camera conditions and clip vision outputs
latentLATENTGenerated video latent representation for use with video models