Nodes/ComfyUI/Bernini Conditioning
ComfyUI Node Runs on cloud

Bernini Conditioning

Conditioning node for Bernini in-context video/image conditioning. It can be used for the following tasks: t2v (text-to-video), v2v (video-to-video), rv2v (reference-guided video editing), r2v (reference-to-video), ads2v (insert image/video into video).Reference images injected as in-context tokens (r2v, rv2v) are encoded independently at their own native aspect ratio (long edge capped at ref_max_size)

By Comfy-Org·Created 4 years ago·Updated 20 days ago· 121,575
Bernini Conditioning
  • positive
  • negative
  • vae
  • source_video
  • reference_video
  • reference_images
  • positive
  • negative
  • latent
width832
height480
length81
batch_size1
ref_max_size848
Categorymodel/conditioning/bernini

Inputs (11)

NameTypeDefaultDescription
positiveCONDITIONING
negativeCONDITIONING
vaeVAE
widthINT83216–8192
heightINT48016–8192
lengthINT811–8192
batch_sizeINT11–4096
source_videooptIMAGESource video to edit or restyle (v2v, rv2v). Resized to width/height and trimmed to length.
reference_videooptIMAGEVideo to insert into the source video (ads2v).
reference_imagesoptCOMFY_AUTOGROW_V3
ref_max_sizeoptINT84816–8192Max size for the long edge of reference_video and reference_images. Resized with preserved aspect ratio and snapped to 16px.

Outputs (3)

NameTypeDescription
positiveCONDITIONING
negativeCONDITIONING
latentLATENT