🖼️ Vision Model Loader (Transformers)

VisionModelLoaderTransformers

🤖 GGUF-VLM/🖼️ Vision Models

Pack: Qwen2.5-VL GGUF Nodes

custom_nodes.ComfyUI-GGUF-VLM

Inputs (6)

Name	Type	Required
model	COMBO	required
quantization	COMBO	required
attention	COMBO	required
keep_model_loaded	BOOLEAN	required
min_pixels	INT	required
max_pixels	INT	required

Outputs (1)

Name	Type
model_config	TRANSFORMERS_MODEL