Nodes/ComfyUI-Toggle-Pass/Ref Image Encode
ComfyUI Node

Ref Image Encode

A ComfyUI node in Toggle-Pass with 20 inputs and 2 outputs.

By electricty00·Created 3 months ago·Updated 3 months ago· 0
Ref Image Encode
  • clip
  • vae
  • image1
  • image2
  • image3
  • image4
  • image5
  • image6
  • image7
  • image8
  • image9
  • image10
  • conditioning
  • latent
num_images1
prompt
instructionDescribe the key features of the input image (color, shape, size, texture, objects, background), then explain how the user's text instruction should alter or modify the image. Generate a new image that meets the user's requirements while maintaining consistency with the original input where appropriate.
模型类型Flux2
匹配原图尺寸OFF
输出宽度1024
输出高度1024
图层数3
CategoryToggle-Pass

Inputs (20)

NameTypeDefaultDescription
clipCLIP
vaeVAE
num_imagesINT11–10
promptSTRING
instructionSTRINGDescribe the key features of the input image (color, shape, size, texture, objects, background), then explain how the user's text instruction should alter or modify the image. Generate a new image that meets the user's requirements while maintaining consistency with the original input where appropriate.
image1optIMAGE
image2optIMAGE
image3optIMAGE
image4optIMAGE
image5optIMAGE
image6optIMAGE
image7optIMAGE
image8optIMAGE
image9optIMAGE
image10optIMAGE
模型类型optCOMBOFlux23 options: Flux2, Qwen Layered, SD / SDXL
匹配原图尺寸optCOMBOOFF2 options: OFF, ON
输出宽度optINT1024256–4096
输出高度optINT1024256–4096
图层数optINT31–64

Outputs (2)

NameTypeDescription
conditioningCONDITIONING
latentLATENT