Nodes/ComfyUI-RH-Bernini-Full/Bernini Full Video to Video
ComfyUI Node

Bernini Full Video to Video

Full Bernini video-to-video editing using Bernini-Diffusers only.

By RH-RunningHub·Created 2 months ago·Updated 2 months ago· 7
Bernini Full Video to Video
  • video
  • video
promptRestyle the source video while preserving motion.
negative_promptlow quality, blurry, distorted, text, watermark
num_frames9
fps16
width0
height0
steps4
seed4567
quality_presetstandard
accelerationwan2.2_lightx2v_4step
memory_modekeep_loaded_batch
CategoryRunningHub/Bernini

Inputs (12)

NameTypeDefaultDescription
videoVIDEOSource video from a ComfyUI video output.
promptSTRINGRestyle the source video while preserving motion.Text prompt or edit instruction.
negative_promptSTRINGlow quality, blurry, distorted, text, watermarkNegative prompt.
num_framesINT95–129Number of output frames. Higher values increase VRAM use and runtime.
fpsINT161–60Frame rate written into the returned video.
widthINT00–20480 follows the source video width.
heightINT00–20480 follows the source video height.
stepsINT41–100Diffusion steps.
seedINT45670–4294967295Random seed. Values are clamped to NumPy's valid 0 to 2**32-1 range before inference.
quality_presetCOMBOstandardstandard balances speed and quality; quality spends more planning time for better output.
accelerationCOMBOwan2.2_lightx2v_4stepAuto-load the Wan2.2 T2V LightX2V 4-step LoRA pair from ComfyUI/models/loras when available.
memory_modeCOMBOkeep_loaded_batchkeep_loaded_batch keeps the Bernini pipeline cached for faster consecutive jobs; low_vram_unload frees memory after each run.

Outputs (1)

NameTypeDescription
videoVIDEO