ComfyUI Node: Qwen3 VL Caption (Inverse Prompt)
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
lang
- 中文
- English
- bbox
seed INT
max_side INT
image IMAGE
video_fps FLOAT
instruction STRING
Outputs
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.