Nodes/ComfyUI-Diffusion-SDXL-Video/Diffusion SDXL Video (Frame by Frame)
ComfyUI Node

Diffusion SDXL Video (Frame by Frame)

Applies Diffusion SDXL for each input image individually and outputs the processed images. Version: 0.1.0

By Polygoningenieur·Created 12 months ago·Updated 11 months ago· 1
Diffusion SDXL Video (Frame by Frame)
  • images
  • model
  • positive
  • negative
  • control_net
  • vae
  • images
cfg8.0
sampler_name
sampler_scheduler
sampler_seed0
sampler_steps20
sampler_denoise1.00
controlnet_strength1.00
controlnet_start_percent0.000
controlnet_end_percent1.000
frame_start1
frame_stop0
frame_step1
Categoryconditioning

Inputs (18)

NameTypeDefaultDescription
imagesIMAGEMultiple Images
modelMODELIC-Light model
positiveCONDITIONING
negativeCONDITIONING
control_netCONTROL_NET
vaeVAE
cfgFLOAT8.00–100Sampling cfg The Classifier-Free Guidance scale balances creativity and adherence to the prompt. Higher values result in images more closely matching the prompt however too high values will negatively impact quality.
sampler_nameCOMBOThe algorithm used when sampling, this can affect the quality, speed, and style of the generated output.
sampler_schedulerCOMBOThe scheduler controls how noise is gradually removed to form the image.
sampler_seedoptINT00–18446744073709550000The random seed used for creating the noise.
sampler_stepsoptINT201–10000The number of steps used in the denoising process.
sampler_denoiseoptFLOAT1.000–1The amount of denoising applied, lower values will maintain the structure of the initial image allowing for image to image sampling.
controlnet_strengthoptFLOAT1.000–10ControlNet Strength
controlnet_start_percentoptFLOAT0.0000–1ControlNet Start Percent
controlnet_end_percentoptFLOAT1.0000–1ControlNet End Percent
frame_startoptINT11–18446744073709550000Frame to start at.
frame_stopoptINT00–18446744073709550000Frame to stop at. Leave at 0 to use all frames.
frame_stepoptINT11–18446744073709550000How much frames to step over each iteration.

Outputs (1)

NameTypeDescription
imagesIMAGE