Nodes/ComfyUI Smart Helper Nodes/Smart TextEncodeEditAdvanced (6 images)
ComfyUI Node

Smart TextEncodeEditAdvanced (6 images)

A ComfyUI node in SmartHelperNodes with 12 inputs and 1 output.

By slvslvslv·Created 2 years ago·Updated 2 months ago· 3
Smart TextEncodeEditAdvanced (6 images)
  • clip
  • vae
  • image1
  • image2
  • image3
  • image4
  • image5
  • image6
  • CONDITIONING
prompt
use_vl_encodingtrue
vl_megapixels0.50
max_images_allowed6
CategorySmartHelperNodes

Inputs (12)

NameTypeDefaultDescription
clipCLIP
promptSTRING
use_vl_encodingBOOLEANtrueEnable VL image feeding: prepend Picture N vision tokens, pass downscaled images to clip.tokenize, and apply the edit-style llama_template. Turn off to behave like plain text encode + reference_latents.
vl_megapixelsFLOAT0.500–4Target megapixels for Vision-Language model. Set to 0 to disable VL image feeding. Recommended: 0.2-1.0 MP. Qwen2.5-VL trained range: 0.2-1.0 MP
max_images_allowedCOMBO6Maximum number of images to process. Images are processed in order: image1..image6
vaeoptVAE
image1optIMAGE
image2optIMAGE
image3optIMAGE
image4optIMAGE
image5optIMAGE
image6optIMAGE

Outputs (1)

NameTypeDescription
CONDITIONINGCONDITIONING