Skip to main content

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.

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The Wan 2.7 Video Continuation node generates a new video segment that continues seamlessly from the end of an input video clip. It uses the Wan 2.7 model to synthesize the continuation based on a text prompt and can optionally guide the ending towards a specific target frame.

Inputs

ParameterData TypeRequiredRangeDescription
modelCOMBOYes"wan2.7-i2v"The video generation model to use.
model.promptSTRINGYes-Prompt describing the elements and visual features. Supports English and Chinese. (default: empty string)
model.negative_promptSTRINGYes-Negative prompt describing what to avoid. (default: empty string)
model.resolutionCOMBOYes"720P"
"1080P"
The resolution for the output video.
model.durationINTYes2 to 15Total output duration in seconds. The model generates continuation to fill the remaining time after the input clip. (default: 5)
first_clipVIDEOYes-Input video to continue from. Duration: 2s-10s. The output aspect ratio is derived from this video.
last_frameIMAGENo-Last frame image. The continuation will transition towards this frame.
seedINTYes0 to 2147483647Seed to use for generation. (default: 0)
prompt_extendBOOLEANYes-Whether to enhance the prompt with AI assistance. (default: True)
watermarkBOOLEANYes-Whether to add an AI-generated watermark to the result. (default: False)
Note: The first_clip input video must be between 2 and 10 seconds in duration.

Outputs

Output NameData TypeDescription
outputVIDEOThe generated video continuation.

Source fingerprint (SHA-256): 44f71824f1289351fe44ff0f830ee391d2387146444f50ba50309ecba2e54456