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 Moonvalley Marey Video to Video node transforms an input video into a new video based on a text description. It uses the Moonvalley API to generate videos that match your prompt while preserving motion or pose characteristics from the original video. You can control the style and content of the output video through text prompts and various generation parameters.

Inputs

ParameterData TypeRequiredRangeDescription
promptSTRINGYes-Describes the video to generate (multiline input)
negative_promptSTRINGNo-Negative prompt text (default: extensive list of negative descriptors)
seedINTYes0-4294967295Random seed value (default: 9)
videoVIDEOYes-The reference video used to generate the output video. Must be at least 5 seconds long. Videos longer than 5s will be automatically trimmed. Only MP4 format supported.
control_typeCOMBONo”Motion Transfer"
"Pose Transfer”
Control type selection (default: “Motion Transfer”)
motion_intensityINTNo0-100Only used if control_type is ‘Motion Transfer’ (default: 100)
stepsINTYes1-100Number of inference steps (default: 33)
Note: The motion_intensity parameter is only applied when control_type is set to “Motion Transfer”. When using “Pose Transfer”, this parameter is ignored.

Outputs

Output NameData TypeDescription
outputVIDEOThe generated video output