Nodes/ComfyUI-Youtu-VL/Youtu-VL (GGUF Advanced)
ComfyUI Node

Youtu-VL (GGUF Advanced)

A ComfyUI node in 🧪AILab/YoutuVL with 11 inputs and 1 output.

By 1038lab·Created 6 months ago·Updated 6 months ago· 13
Youtu-VL (GGUF Advanced)
  • image
  • text
modelYoutu-VL-4B-Instruct-GGUF-Q8
n_gpu_layers-1
n_ctx4096
preset_prompt🖼️ Describe Image
custom_prompt
max_tokens512
temperature0.10
top_p0.001
keep_model_loadedtrue
seed1
Category🧪AILab/YoutuVL

Inputs (11)

NameTypeDefaultDescription
modelCOMBOYoutu-VL-4B-Instruct-GGUF-Q8Select the GGUF quantized model.
n_gpu_layersINT-1-1–100Number of layers to offload to GPU. -1 = all layers.
n_ctxINT4096512–32768Context window size.
preset_promptCOMBO🖼️ Describe Image6 options: 🖼️ Describe Image, 📝 Detailed Description, 🔍 Analyze Elements, 🏷️ Generate Tags, 📄 OCR Text, 🎨 Art Style Analysis
custom_promptSTRING
max_tokensINT51264–32768Maximum number of new tokens to generate.
temperatureFLOAT0.100.01–2Sampling temperature. Lower = more focused.
top_pFLOAT0.0010.001–1Nucleus sampling cutoff.
keep_model_loadedBOOLEANtrueKeep model loaded for faster subsequent inference.
seedINT11–4294967295
imageoptIMAGE

Outputs (1)

NameTypeDescription
textSTRING