ComfyUI Node: Qwen3.5 VL Caption (Inverse Prompt)

Authored by WingeD123

Created

Updated

42 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Category

image/caption

Inputs

model_path
    dtype
    • auto
    • 4bit
    • 8bit
    keep_model_loaded BOOLEAN
    unload_other_models BOOLEAN
    thinking BOOLEAN
    lang
    • 中文
    • English
    • bbox
    seed INT
    max_side INT
    image IMAGE
    video_fps FLOAT
    instruction STRING

    Outputs

    STRING

    STRING

    Extension: ComfyUI_QwenVL_PromptCaption

    Leverages Qwen 2.5/3 VL for prompt inversion & caption generation.

    Authored by WingeD123

    Looking for a different node?

    Run ComfyUI workflows without the setup

    No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

    Learn more