Skip to main content
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

ParameterDescriptionData TypeRequiredRange
modelThe video generation model to use.COMBOYes"wan2.7-i2v"
model.promptPrompt describing the elements and visual features. Supports English and Chinese. (default: empty string)STRINGYes-
model.negative_promptNegative prompt describing what to avoid. (default: empty string)STRINGYes-
model.resolutionThe resolution for the output video.COMBOYes"720P"
"1080P"
model.durationTotal output duration in seconds. The model generates continuation to fill the remaining time after the input clip. (default: 5)INTYes2 to 15
first_clipInput video to continue from. Duration: 2s-10s. The output aspect ratio is derived from this video.VIDEOYes-
last_frameLast frame image. The continuation will transition towards this frame.IMAGENo-
seedSeed to use for generation. (default: 0)INTYes0 to 2147483647
prompt_extendWhether to enhance the prompt with AI assistance. (default: True)BOOLEANYes-
watermarkWhether to add an AI-generated watermark to the result. (default: False)BOOLEANYes-
Note: The first_clip input video must be between 2 and 10 seconds in duration.

Outputs

Output NameDescriptionData Type
outputThe generated video continuation.VIDEO
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 44f71824f1289351fe44ff0f830ee391d2387146444f50ba50309ecba2e54456