Nodes/ComfyUI-Apt_Preset/sum_stack_QwenEditPlus
ComfyUI Node

sum_stack_QwenEditPlus

vl_size:视觉尺寸越大,提取的图像特征越丰富。 auto_resize: 缩放模式(crop=中心裁剪,pad=中心黑色填充,stretch=强制拉伸) system_prompt:系统提示词,用于指导图像特征描述与修改逻辑(默认提供基础配置) latent_image: 生成图尺寸。 latent_mask: 生成图遮罩

By cardenluo·Created 2 years ago·Updated 18 days ago· 309
sum_stack_QwenEditPlus
  • context
  • model
  • lora_stack
  • image1
  • image2
  • image3
  • union_controlnet
  • latent_image
  • latent_mask
  • context
  • model
  • positive
  • negative
  • latent
  • clip
  • vae
vl_size384
auto_resizecrop
prompt
system_promptDescribe 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.
image1_strength1.00
image2_strength1.00
image3_strength1.00
CategoryApt_Preset/chx_tool

Inputs (16)

NameTypeDefaultDescription
contextRUN_CONTEXT
modeloptMODEL
lora_stackoptLORASTACK
image1optIMAGE
image2optIMAGE
image3optIMAGE
union_controlnetoptUNION_STACK
vl_sizeoptINT38464–2048
auto_resizeoptCOMBOcrop3 options: crop, pad, stretch
promptoptSTRING
system_promptoptSTRINGDescribe 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.
latent_imageoptIMAGE
latent_maskoptMASK
image1_strengthoptFLOAT1.000–10
image2_strengthoptFLOAT1.000–10
image3_strengthoptFLOAT1.000–10

Outputs (7)

NameTypeDescription
contextRUN_CONTEXT
modelMODEL
positiveCONDITIONING
negativeCONDITIONING
latentLATENT
clipCLIP
vaeVAE