Nodes/ComfyUI-Ollama-ImageList/CLIP Generate Text (Image List)
ComfyUI Node

CLIP Generate Text (Image List)

Extends ComfyUI Generate Text with a system role and one-call IMAGE LIST support.

By craftingmod·Created 19 days ago·Updated 9 days ago· 2
CLIP Generate Text (Image List)
  • clip
  • images
  • video
  • audio
  • generated_text
system
prompt
model_formatauto
max_length512
sampling_mode
thinkingfalse
use_default_templatetrue
CategoryOllama/CLIP

Inputs (11)

NameTypeDefaultDescription
clipCLIP
systemSTRING
promptSTRING
model_formatCOMBOautoAuto-detect the tokenizer, or manually select its chat format.
max_lengthINT5121–32768
sampling_modeCOMBO2 options: [object Object], [object Object]
imagesoptIMAGE
videooptIMAGEVideo frames as one IMAGE batch; assumed to be 24 FPS.
audiooptAUDIO
thinkingoptBOOLEANfalseOperate in thinking mode if the model supports it.
use_default_templateoptBOOLEANtrueApply the model chat template. Disable only when prompt already contains the complete model-specific template.

Outputs (1)

NameTypeDescription
generated_textSTRING