Nodes/ComfyUI_QwenVL_PromptCaption/Qwen3 VL Caption (Inverse Prompt)
ComfyUI Node

Qwen3 VL Caption (Inverse Prompt)

A ComfyUI node in image/caption with 10 inputs and 1 output.

By WingeD123·Created 9 months ago·Updated 3 months ago· 42
Qwen3 VL Caption (Inverse Prompt)
  • image
  • text
model_path
dtypeauto
keep_model_loadedfalse
unload_other_modelstrue
lang中文
seed1
max_side512
video_fps16.0
instruction
Categoryimage/caption

Inputs (10)

NameTypeDefaultDescription
model_pathCOMBO0 options:
dtypeCOMBOauto3 options: auto, 4bit, 8bit
keep_model_loadedBOOLEANfalse
unload_other_modelsBOOLEANtrue
langCOMBO中文3 options: 中文, English, bbox
seedINT10–4294967295
max_sideINT512256–2240
imageoptIMAGE
video_fpsoptFLOAT16.01–200
instructionoptSTRING

Outputs (1)

NameTypeDescription
textSTRING