Nodes/ComfyUI-QwenVL-F/QwenVL-F Advanced (GGUF)
ComfyUI Node

QwenVL-F Advanced (GGUF)

A ComfyUI node in QwenVL-F with 25 inputs and 1 output.

By id-fa·Created 5 months ago·Updated 9 days ago· 1
QwenVL-F Advanced (GGUF)
  • image
  • image2
  • image3
  • video
  • RESPONSE
model_name(no models found — see console)
mmproj_nameauto
deviceauto
preset_prompt🖼️ Detailed Description
custom_prompt
max_tokens512
temperature0.60
top_p0.90
repetition_penalty1.20
frame_count16
ctx32768
n_batch8192
gpu_layers-1
image_max_tokens8192
image_min_tokens1024
top_k0
pool_size4194304
enable_thinkingfalse
stop_words
keep_model_loadedtrue
seed1
CategoryQwenVL-F

Inputs (25)

NameTypeDefaultDescription
model_nameCOMBO(no models found — see console)Pick a .gguf already present under models/text_encoders or models/LLM. Nothing is downloaded automatically — copy the file in yourself, then reload ComfyUI.
mmproj_nameCOMBOautoVision projector to pair with the model. auto picks the first *mmproj*.gguf sitting next to it.
deviceCOMBOauto3 options: auto, cpu, mps
preset_promptCOMBO🖼️ Detailed Description9 options: 🖼️ Tags, 🖼️ Simple Description, 🖼️ Detailed Description, 🖼️ Ultra Detailed Description, 🎬 Cinematic Description, 🖼️ Detailed Analysis, +3
custom_promptSTRING
max_tokensINT51264–32768
temperatureFLOAT0.600–2
top_pFLOAT0.900–1
repetition_penaltyFLOAT1.200.5–2
frame_countINT161–64
ctxINT327681024–262144
n_batchINT819264–32768
gpu_layersINT-1-1–200
image_max_tokensINT8192256–1024000
image_min_tokensINT102464–1024000
top_kINT00–32768
pool_sizeINT41943041048576–10485760
enable_thinkingBOOLEANfalse
stop_wordsSTRING
keep_model_loadedBOOLEANtrue
seedINT11–4294967295
imageoptIMAGE
image2optIMAGE
image3optIMAGE
videooptIMAGE

Outputs (1)

NameTypeDescription
RESPONSESTRING