Nodes/ComfyUI/Wan Reference to Video
ComfyUI Node Runs on cloud

Wan Reference to Video

Use the character and voice from input videos, combined with a prompt, to generate a new video that maintains character consistency.

By Comfy-Org·Created 4 years ago·Updated 15 days ago· 121,575
Wan Reference to Video
  • reference_videos
  • VIDEO
model
prompt
negative_prompt
size
duration5
seed0
shot_type
watermarkfalse
Categorypartner/video/Wan

Inputs (9)

NameTypeDefaultDescription
modelCOMBO1 options: wan2.6-r2v
promptSTRINGPrompt describing the elements and visual features. Supports English and Chinese. Use identifiers such as `character1` and `character2` to refer to the reference characters.
negative_promptSTRINGNegative prompt describing what to avoid.
reference_videosCOMFY_AUTOGROW_V3
sizeCOMBO10 options: 720p: 1:1 (960x960), 720p: 16:9 (1280x720), 720p: 9:16 (720x1280), 720p: 4:3 (1088x832), 720p: 3:4 (832x1088), 1080p: 1:1 (1440x1440), +4
durationINT55–10
seedINT00–2147483647
shot_typeCOMBOSpecifies the shot type for the generated video, that is, whether the video is a single continuous shot or multiple shots with cuts.
watermarkBOOLEANfalseWhether to add an AI-generated watermark to the result.

Outputs (1)

NameTypeDescription
VIDEOVIDEO